Add files via upload

Fix some typos in Notebooks/Chap05/5_1_Least_Squares_Loss.ipynb

Blogs/BorealisGradientFlow.ipynb

@@ -0,0 +1,401 @@
+{
+  "nbformat": 4,
+  "nbformat_minor": 0,
+  "metadata": {
+    "colab": {
+      "provenance": [],
+      "authorship_tag": "ABX9TyO6cFY1oR4CmbHL2QywgTXm",
+      "include_colab_link": true
+    },
+    "kernelspec": {
+      "name": "python3",
+      "display_name": "Python 3"
+    },
+    "language_info": {
+      "name": "python"
+    }
+  },
+  "cells": [
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "view-in-github",
+        "colab_type": "text"
+      },
+      "source": [
+        "<a href=\"https://colab.research.google.com/github/udlbook/udlbook/blob/main/Blogs/BorealisGradientFlow.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "# Gradient flow\n",
+        "\n",
+        "This notebook replicates some of the results in the the Borealis AI blog on gradient flow.  \n"
+      ],
+      "metadata": {
+        "id": "ucrRRJ4dq8_d"
+      }
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "# Import relevant libraries\n",
+        "import numpy as np\n",
+        "import matplotlib.pyplot as plt\n",
+        "from scipy.linalg import expm\n",
+        "from matplotlib import cm\n",
+        "from matplotlib.colors import ListedColormap"
+      ],
+      "metadata": {
+        "id": "_IQFHZEMZE8T"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "Create the three data points that are used to train the linear model in the blog.  Each input point is a column in $\\mathbf{X}$ and consists of the $x$ position in the plot and the value 1, which is used to allow the model to fit bias terms neatly."
+      ],
+      "metadata": {
+        "id": "NwgUP3MSriiJ"
+      }
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "cJNZ2VIcYsD8"
+      },
+      "outputs": [],
+      "source": [
+        "X = np.array([[0.2, 0.4, 0.8],[1,1,1]])\n",
+        "y = np.array([[-0.1],[0.15],[0.3]])\n",
+        "D = X.shape[0]\n",
+        "I  = X.shape[1]\n",
+        "\n",
+        "print(\"X=\\n\",X)\n",
+        "print(\"y=\\n\",y)"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "# Draw the three data points\n",
+        "fig, ax  = plt.subplots()\n",
+        "ax.plot(X[0:1,:],y.T,'ro')\n",
+        "ax.set_xlim([0,1]); ax.set_ylim([-0.5,0.5])\n",
+        "ax.set_xlabel('x'); ax.set_ylabel('y')\n",
+        "plt.show()"
+      ],
+      "metadata": {
+        "id": "FpFlD4nUZDRt"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "Compute the evolution of the residuals, loss, and parameters as a function of time."
+      ],
+      "metadata": {
+        "id": "H2LBR1DasQej"
+      }
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "# Discretized time to evaluate quantities at\n",
+        "t_all = np.arange(0,20,0.01)\n",
+        "nT = t_all.shape[0]\n",
+        "\n",
+        "# Initial parameters, and initial function output at training points\n",
+        "phi_0 = np.array([[-0.05],[-0.4]])\n",
+        "f_0 = X.T @ phi_0\n",
+        "\n",
+        "# Precompute pseudoinverse term (not a very sensible numerical implementation, but it works...)\n",
+        "XXTInvX = np.linalg.inv(X@X.T)@X\n",
+        "\n",
+        "# Create arrays to hold function at data points over time, residual over time, parameters over time\n",
+        "f_all = np.zeros((I,nT))\n",
+        "f_minus_y_all = np.zeros((I,nT))\n",
+        "phi_t_all = np.zeros((D,nT))\n",
+        "\n",
+        "# For each time, compute function, residual, and parameters at each time.\n",
+        "for t in range(len(t_all)):\n",
+        "  f = y + expm(-X.T@X * t_all[t]) @ (f_0-y)\n",
+        "  f_all[:,t:t+1] = f\n",
+        "  f_minus_y_all[:,t:t+1] = f-y\n",
+        "  phi_t_all[:,t:t+1] = phi_0 - XXTInvX @ (np.identity(3)-expm(-X.T@X * t_all[t])) @ (f_0-y)"
+      ],
+      "metadata": {
+        "id": "wfF_oTS5Z4Wi"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "Plot the results that were calculated in the previous cell"
+      ],
+      "metadata": {
+        "id": "9jSjOOFutJUE"
+      }
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "# Plot function at data points\n",
+        "fig, ax  = plt.subplots()\n",
+        "ax.plot(t_all,np.squeeze(f_all[0,:]),'r-', label='$f[x_{0},\\phi]$')\n",
+        "ax.plot(t_all,np.squeeze(f_all[1,:]),'g-', label='$f[x_{1},\\phi]$')\n",
+        "ax.plot(t_all,np.squeeze(f_all[2,:]),'b-', label='$f[x_{2},\\phi]$')\n",
+        "ax.set_xlim([0,np.max(t_all)]); ax.set_ylim([-0.5,0.5])\n",
+        "ax.set_xlabel('t'); ax.set_ylabel('f')\n",
+        "plt.legend(loc=\"lower right\")\n",
+        "plt.show()\n",
+        "\n",
+        "# Plot residual\n",
+        "fig, ax  = plt.subplots()\n",
+        "ax.plot(t_all,np.squeeze(f_minus_y_all[0,:]),'r-', label='$f[x_{0},\\phi]-y_{0}$')\n",
+        "ax.plot(t_all,np.squeeze(f_minus_y_all[1,:]),'g-', label='$f[x_{1},\\phi]-y_{1}$')\n",
+        "ax.plot(t_all,np.squeeze(f_minus_y_all[2,:]),'b-', label='$f[x_{2},\\phi]-y_{2}$')\n",
+        "ax.set_xlim([0,np.max(t_all)]); ax.set_ylim([-0.5,0.5])\n",
+        "ax.set_xlabel('t'); ax.set_ylabel('f-y')\n",
+        "plt.legend(loc=\"lower right\")\n",
+        "plt.show()\n",
+        "\n",
+        "# Plot loss (sum of residuals)\n",
+        "fig, ax  = plt.subplots()\n",
+        "square_error = 0.5 * np.sum(f_minus_y_all * f_minus_y_all, axis=0)\n",
+        "ax.plot(t_all, square_error,'k-')\n",
+        "ax.set_xlim([0,np.max(t_all)]); ax.set_ylim([-0.0,0.25])\n",
+        "ax.set_xlabel('t'); ax.set_ylabel('Loss')\n",
+        "plt.show()\n",
+        "\n",
+        "# Plot parameters\n",
+        "fig, ax  = plt.subplots()\n",
+        "ax.plot(t_all, np.squeeze(phi_t_all[0,:]),'c-',label='$\\phi_{0}$')\n",
+        "ax.plot(t_all, np.squeeze(phi_t_all[1,:]),'m-',label='$\\phi_{1}$')\n",
+        "ax.set_xlim([0,np.max(t_all)]); ax.set_ylim([-1,1])\n",
+        "ax.set_xlabel('t'); ax.set_ylabel('$\\phi$')\n",
+        "plt.legend(loc=\"lower right\")\n",
+        "plt.show()"
+      ],
+      "metadata": {
+        "id": "G9IwgwKltHz5"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "Define the model and the loss function"
+      ],
+      "metadata": {
+        "id": "N6VaUq2swa8D"
+      }
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "# Model is just a straight line with intercept phi[0] and slope phi[1]\n",
+        "def model(phi,x):\n",
+        "  y_pred = phi[0]+phi[1] * x\n",
+        "  return y_pred\n",
+        "\n",
+        "# Loss function is 0.5 times sum of squares of residuals for training data\n",
+        "def compute_loss(data_x, data_y, model, phi):\n",
+        "  pred_y = model(phi, data_x)\n",
+        "  loss = 0.5 * np.sum((pred_y-data_y)*(pred_y-data_y))\n",
+        "  return loss"
+      ],
+      "metadata": {
+        "id": "LGHEVUWWiB4f"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "Draw the loss function"
+      ],
+      "metadata": {
+        "id": "hr3hs7pKwo0g"
+      }
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "def draw_loss_function(compute_loss, X, y,  model, phi_iters):\n",
+        "  # Define pretty colormap\n",
+        "  my_colormap_vals_hex =('2a0902', '2b0a03', '2c0b04', '2d0c05', '2e0c06', '2f0d07', '300d08', '310e09', '320f0a', '330f0b', '34100b', '35110c', '36110d', '37120e', '38120f', '39130f', '3a1410', '3b1411', '3c1511', '3d1612', '3e1613', '3f1713', '401714', '411814', '421915', '431915', '451a16', '461b16', '471b17', '481c17', '491d18', '4a1d18', '4b1e19', '4c1f19', '4d1f1a', '4e201b', '50211b', '51211c', '52221c', '53231d', '54231d', '55241e', '56251e', '57261f', '58261f', '592720', '5b2821', '5c2821', '5d2922', '5e2a22', '5f2b23', '602b23', '612c24', '622d25', '632e25', '652e26', '662f26', '673027', '683027', '693128', '6a3229', '6b3329', '6c342a', '6d342a', '6f352b', '70362c', '71372c', '72372d', '73382e', '74392e', '753a2f', '763a2f', '773b30', '783c31', '7a3d31', '7b3e32', '7c3e33', '7d3f33', '7e4034', '7f4134', '804235', '814236', '824336', '834437', '854538', '864638', '874739', '88473a', '89483a', '8a493b', '8b4a3c', '8c4b3c', '8d4c3d', '8e4c3e', '8f4d3f', '904e3f', '924f40', '935041', '945141', '955242', '965343', '975343', '985444', '995545', '9a5646', '9b5746', '9c5847', '9d5948', '9e5a49', '9f5a49', 'a05b4a', 'a15c4b', 'a35d4b', 'a45e4c', 'a55f4d', 'a6604e', 'a7614e', 'a8624f', 'a96350', 'aa6451', 'ab6552', 'ac6552', 'ad6653', 'ae6754', 'af6855', 'b06955', 'b16a56', 'b26b57', 'b36c58', 'b46d59', 'b56e59', 'b66f5a', 'b7705b', 'b8715c', 'b9725d', 'ba735d', 'bb745e', 'bc755f', 'bd7660', 'be7761', 'bf7862', 'c07962', 'c17a63', 'c27b64', 'c27c65', 'c37d66', 'c47e67', 'c57f68', 'c68068', 'c78169', 'c8826a', 'c9836b', 'ca846c', 'cb856d', 'cc866e', 'cd876f', 'ce886f', 'ce8970', 'cf8a71', 'd08b72', 'd18c73', 'd28d74', 'd38e75', 'd48f76', 'd59077', 'd59178', 'd69279', 'd7937a', 'd8957b', 'd9967b', 'da977c', 'da987d', 'db997e', 'dc9a7f', 'dd9b80', 'de9c81', 'de9d82', 'df9e83', 'e09f84', 'e1a185', 'e2a286', 'e2a387', 'e3a488', 'e4a589', 'e5a68a', 'e5a78b', 'e6a88c', 'e7aa8d', 'e7ab8e', 'e8ac8f', 'e9ad90', 'eaae91', 'eaaf92', 'ebb093', 'ecb295', 'ecb396', 'edb497', 'eeb598', 'eeb699', 'efb79a', 'efb99b', 'f0ba9c', 'f1bb9d', 'f1bc9e', 'f2bd9f', 'f2bfa1', 'f3c0a2', 'f3c1a3', 'f4c2a4', 'f5c3a5', 'f5c5a6', 'f6c6a7', 'f6c7a8', 'f7c8aa', 'f7c9ab', 'f8cbac', 'f8ccad', 'f8cdae', 'f9ceb0', 'f9d0b1', 'fad1b2', 'fad2b3', 'fbd3b4', 'fbd5b6', 'fbd6b7', 'fcd7b8', 'fcd8b9', 'fcdaba', 'fddbbc', 'fddcbd', 'fddebe', 'fddfbf', 'fee0c1', 'fee1c2', 'fee3c3', 'fee4c5', 'ffe5c6', 'ffe7c7', 'ffe8c9', 'ffe9ca', 'ffebcb', 'ffeccd', 'ffedce', 'ffefcf', 'fff0d1', 'fff2d2', 'fff3d3', 'fff4d5', 'fff6d6', 'fff7d8', 'fff8d9', 'fffada', 'fffbdc', 'fffcdd', 'fffedf', 'ffffe0')\n",
+        "  my_colormap_vals_dec = np.array([int(element,base=16) for element in my_colormap_vals_hex])\n",
+        "  r = np.floor(my_colormap_vals_dec/(256*256))\n",
+        "  g = np.floor((my_colormap_vals_dec - r *256 *256)/256)\n",
+        "  b = np.floor(my_colormap_vals_dec - r * 256 *256 - g * 256)\n",
+        "  my_colormap = ListedColormap(np.vstack((r,g,b)).transpose()/255.0)\n",
+        "\n",
+        "  # Make grid of intercept/slope values to plot\n",
+        "  intercepts_mesh, slopes_mesh = np.meshgrid(np.arange(-1.0,1.0,0.005), np.arange(-1.0,1.0,0.005))\n",
+        "  loss_mesh = np.zeros_like(slopes_mesh)\n",
+        "  # Compute loss for every set of parameters\n",
+        "  for idslope, slope in np.ndenumerate(slopes_mesh):\n",
+        "     loss_mesh[idslope] = compute_loss(X, y, model, np.array([[intercepts_mesh[idslope]], [slope]]))\n",
+        "\n",
+        "  fig,ax = plt.subplots()\n",
+        "  fig.set_size_inches(8,8)\n",
+        "  ax.contourf(intercepts_mesh,slopes_mesh,loss_mesh,256,cmap=my_colormap)\n",
+        "  ax.contour(intercepts_mesh,slopes_mesh,loss_mesh,40,colors=['#80808080'])\n",
+        "  ax.set_ylim([1,-1]); ax.set_xlim([-1,1])\n",
+        "\n",
+        "  ax.plot(phi_iters[1,:], phi_iters[0,:],'g-')\n",
+        "  ax.set_xlabel('Intercept'); ax.set_ylabel('Slope')\n",
+        "  plt.show()"
+      ],
+      "metadata": {
+        "id": "UCxa3tZ8a9kz"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "draw_loss_function(compute_loss, X[0:1,:], y.T, model, phi_t_all)"
+      ],
+      "metadata": {
+        "id": "pXLLBaSaiI2A"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "Draw the evolution of the function"
+      ],
+      "metadata": {
+        "id": "ZsremHW-xFi5"
+      }
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "fig, ax  = plt.subplots()\n",
+        "ax.plot(X[0:1,:],y.T,'ro')\n",
+        "x_vals = np.arange(0,1,0.001)\n",
+        "ax.plot(x_vals, phi_t_all[0,0]*x_vals + phi_t_all[1,0],'r-', label='t=0.00')\n",
+        "ax.plot(x_vals, phi_t_all[0,10]*x_vals + phi_t_all[1,10],'g-', label='t=0.10')\n",
+        "ax.plot(x_vals, phi_t_all[0,30]*x_vals + phi_t_all[1,30],'b-', label='t=0.30')\n",
+        "ax.plot(x_vals, phi_t_all[0,200]*x_vals + phi_t_all[1,200],'c-', label='t=2.00')\n",
+        "ax.plot(x_vals, phi_t_all[0,1999]*x_vals + phi_t_all[1,1999],'y-', label='t=20.0')\n",
+        "ax.set_xlim([0,1]); ax.set_ylim([-0.5,0.5])\n",
+        "ax.set_xlabel('x'); ax.set_ylabel('y')\n",
+        "plt.legend(loc=\"upper left\")\n",
+        "plt.show()"
+      ],
+      "metadata": {
+        "id": "cv9ZrUoRkuhI"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "# Compute MAP and ML solutions\n",
+        "MLParams = np.linalg.inv(X@X.T)@X@y\n",
+        "sigma_sq_p = 3.0\n",
+        "sigma_sq = 0.05\n",
+        "MAPParams = np.linalg.inv(X@X.T+np.identity(X.shape[0])*sigma_sq/sigma_sq_p)@X@y"
+      ],
+      "metadata": {
+        "id": "OU9oegSOof-o"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "Finally, we predict both the mean and the uncertainty in the fitted model as a function of time"
+      ],
+      "metadata": {
+        "id": "Ul__XvOgyYSA"
+      }
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "# Define x positions to make predictions (appending a 1 to each column)\n",
+        "x_predict = np.arange(0,1,0.01)[None,:]\n",
+        "x_predict = np.concatenate((x_predict,np.ones_like(x_predict)))\n",
+        "nX = x_predict.shape[1]\n",
+        "\n",
+        "# Create variables to store evolution of mean and variance of prediction over time\n",
+        "predict_mean_all = np.zeros((nT,nX))\n",
+        "predict_var_all = np.zeros((nT,nX))\n",
+        "\n",
+        "# Initial covariance\n",
+        "sigma_sq_p = 2.0\n",
+        "cov_init = sigma_sq_p * np.identity(2)\n",
+        "\n",
+        "# Run through each time computing a and b and hence mean and variance of prediction\n",
+        "for t in range(len(t_all)):\n",
+        "  a = x_predict.T @(XXTInvX @ (np.identity(3)-expm(-X.T@X * t_all[t])) @ y)\n",
+        "  b = x_predict.T -x_predict.T@XXTInvX @ (np.identity(3)-expm(-X.T@X * t_all[t])) @ X.T\n",
+        "  predict_mean_all[t:t+1,:] = a.T\n",
+        "  predict_cov  = b@ cov_init @b.T\n",
+        "  # We just want the diagonal of the covariance to plot the uncertainty\n",
+        "  predict_var_all[t:t+1,:] = np.reshape(np.diag(predict_cov),(1,nX))"
+      ],
+      "metadata": {
+        "id": "aMPADCuByKWr"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "Plot the mean and variance at various times"
+      ],
+      "metadata": {
+        "id": "PZTj93KK7QH6"
+      }
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "def plot_mean_var(X,y,x_predict, predict_mean_all, predict_var_all, this_t, sigma_sq = 0.00001):\n",
+        "  fig, ax  = plt.subplots()\n",
+        "  ax.plot(X[0:1,:],y.T,'ro')\n",
+        "  ax.plot(x_predict[0:1,:].T, predict_mean_all[this_t:this_t+1,:].T,'r-')\n",
+        "  lower = np.squeeze(predict_mean_all[this_t:this_t+1,:].T-np.sqrt(predict_var_all[this_t:this_t+1,:].T+np.sqrt(sigma_sq)))\n",
+        "  upper = np.squeeze(predict_mean_all[this_t:this_t+1,:].T+np.sqrt(predict_var_all[this_t:this_t+1,:].T+np.sqrt(sigma_sq)))\n",
+        "  ax.fill_between(np.squeeze(x_predict[0:1,:]), lower, upper, color='lightgray')\n",
+        "  ax.set_xlim([0,1]); ax.set_ylim([-0.5,0.5])\n",
+        "  ax.set_xlabel('x'); ax.set_ylabel('y')\n",
+        "  plt.show()\n",
+        "\n",
+        "plot_mean_var(X,y,x_predict, predict_mean_all, predict_var_all, this_t=0)\n",
+        "plot_mean_var(X,y,x_predict, predict_mean_all, predict_var_all, this_t=40)\n",
+        "plot_mean_var(X,y,x_predict, predict_mean_all, predict_var_all, this_t=80)\n",
+        "plot_mean_var(X,y,x_predict, predict_mean_all, predict_var_all, this_t=200)\n",
+        "plot_mean_var(X,y,x_predict, predict_mean_all, predict_var_all, this_t=500)\n",
+        "plot_mean_var(X,y,x_predict, predict_mean_all, predict_var_all, this_t=1000)"
+      ],
+      "metadata": {
+        "id": "bYAFxgB880-v"
+      },
+      "execution_count": null,
+      "outputs": []
+    }
+  ]
+}

CM20315/CM20315_Convolution_II.ipynb

@@ -105,7 +105,7 @@
       "cell_type": "code",
       "source": [
         "\n",
-        "# TODO Create a model with the folowing layers\n",
+        "# TODO Create a model with the following layers\n",
         "# 1. Convolutional layer, (input=length 40 and 1 channel, kernel size 3x3, stride 2, padding=\"valid\", 15 output channels ) \n",
         "# 2. ReLU\n",
         "# 3. Convolutional layer, (input=length 19 and 15 channels, kernel size 3x3, stride 2, padding=\"valid\", 15 output channels )\n",
@@ -120,7 +120,7 @@
         "# https://pytorch.org/docs/1.13/generated/torch.nn.Linear.html?highlight=linear#torch.nn.Linear\n",
         "\n",
         "# Replace the following function which just runs a standard fully connected network\n",
-        "# The flatten at the beginning is becuase we are passing in the data in a slightly different format.\n",
+        "# The flatten at the beginning is because we are passing in the data in a slightly different format.\n",
         "model = nn.Sequential(\n",
         "nn.Flatten(),\n",
         "nn.Linear(40, 100),\n",

CM20315/CM20315_Convolution_III.ipynb

@@ -148,7 +148,7 @@
         "# 8. A flattening operation\n",
         "# 9. A fully connected layer mapping from (whatever dimensions we are at-- find out using .shape) to 50 \n",
         "# 10. A ReLU\n",
-        "# 11. A fully connected layer mappiing from 50 to 10 dimensions\n",
+        "# 11. A fully connected layer mapping from 50 to 10 dimensions\n",
         "# 12. A softmax function.\n",
         "\n",
         "# Replace this class which implements a minimal network (which still does okay)\n",

CM20315/CM20315_Gradients_II.ipynb

@@ -32,7 +32,7 @@
       "source": [
         "# Gradients II: Backpropagation algorithm\n",
         "\n",
-        "In this practical, we'll investigate the backpropagation algoritithm.  This computes the gradients of the loss with respect to all of the parameters (weights and biases) in the network.  We'll use these gradients when we run stochastic gradient descent."
+        "In this practical, we'll investigate the backpropagation algorithm.  This computes the gradients of the loss with respect to all of the parameters (weights and biases) in the network.  We'll use these gradients when we run stochastic gradient descent."
       ],
       "metadata": {
         "id": "L6chybAVFJW2"
@@ -53,7 +53,7 @@
     {
       "cell_type": "markdown",
       "source": [
-        "First let's define a neural network.  We'll just choose the weights and biaes randomly for now"
+        "First let's define a neural network.  We'll just choose the weights and biases randomly for now"
       ],
       "metadata": {
         "id": "nnUoI0m6GyjC"
@@ -178,7 +178,7 @@
     {
       "cell_type": "markdown",
       "source": [
-        "Now let's define a loss function.  We'll just use the least squaures loss function. We'll also write a function to compute dloss_doutpu"
+        "Now let's define a loss function.  We'll just use the least squares loss function. We'll also write a function to compute dloss_doutpu"
       ],
       "metadata": {
         "id": "SxVTKp3IcoBF"

CM20315/CM20315_Gradients_III.ipynb

@@ -53,7 +53,7 @@
     {
       "cell_type": "markdown",
       "source": [
-        "First let's define a neural network.  We'll just choose the weights and biaes randomly for now"
+        "First let's define a neural network.  We'll just choose the weights and biases randomly for now"
       ],
       "metadata": {
         "id": "nnUoI0m6GyjC"
@@ -204,7 +204,7 @@
     {
       "cell_type": "markdown",
       "source": [
-        "Now let's define a loss function.  We'll just use the least squaures loss function. We'll also write a function to compute dloss_doutput\n"
+        "Now let's define a loss function.  We'll just use the least squares loss function. We'll also write a function to compute dloss_doutput\n"
       ],
       "metadata": {
         "id": "SxVTKp3IcoBF"

CM20315/CM20315_Intro.ipynb

@@ -176,7 +176,7 @@
         "# Color represents y value (brighter = higher value)\n",
         "# Black = -10 or less, White = +10 or more\n",
         "# 0 = mid orange\n",
-        "# Lines are conoturs where value is equal\n",
+        "# Lines are contours where value is equal\n",
         "draw_2D_function(x1,x2,y)\n",
         "\n",
         "# TODO\n",

CM20315/CM20315_Intro_Answers.ipynb

@@ -215,7 +215,7 @@
         "# Color represents y value (brighter = higher value)\n",
         "# Black = -10 or less, White = +10 or more\n",
         "# 0 = mid orange\n",
-        "# Lines are conoturs where value is equal\n",
+        "# Lines are contours where value is equal\n",
         "draw_2D_function(x1,x2,y)\n",
         "\n",
         "# TODO\n",

CM20315/CM20315_Loss.ipynb

@@ -36,7 +36,7 @@
         "\n",
         "We'll compute loss functions for maximum likelihood, minimum negative log likelihood, and least squares and show that they all imply that we should use the same parameter values\n",
         "\n",
-        "In part II, we'll investigate binary classification (where the output data is 0 or 1).  This will be based on the Bernouilli distribution\n",
+        "In part II, we'll investigate binary classification (where the output data is 0 or 1).  This will be based on the Bernoulli distribution\n",
         "\n",
         "In part III we'll investigate multiclass classification (where the output data is 0,1, or, 2).  This will be based on the categorical distribution."
       ],
@@ -178,7 +178,7 @@
     {
       "cell_type": "markdown",
       "source": [
-        "The blue line i sthe mean prediction of the model and the gray area represents plus/minus two standardard deviations.  This model fits okay, but could be improved. Let's compute the loss.  We'll compute the  the least squares error, the likelihood, the negative log likelihood."
+        "The blue line is the mean prediction of the model and the gray area represents plus/minus two standard deviations.  This model fits okay, but could be improved. Let's compute the loss.  We'll compute the  the least squares error, the likelihood, the negative log likelihood."
       ],
       "metadata": {
         "id": "MvVX6tl9AEXF"
@@ -276,7 +276,7 @@
         "beta_0, omega_0, beta_1, omega_1 = get_parameters()\n",
         "# Use our neural network to predict the mean of the Gaussian\n",
         "mu_pred = shallow_nn(x_train, beta_0, omega_0, beta_1, omega_1)\n",
-        "# Set the standard devation to something reasonable\n",
+        "# Set the standard deviation to something reasonable\n",
         "sigma = 0.2\n",
         "# Compute the likelihood\n",
         "likelihood = compute_likelihood(y_train, mu_pred, sigma)\n",
@@ -292,7 +292,7 @@
     {
       "cell_type": "markdown",
       "source": [
-        "You can see that this gives a very small answer, even for this small 1D dataset, and with the model fitting quite well.  This is because it is the product of sveral probabilities, which are all quite small themselves.\n",
+        "You can see that this gives a very small answer, even for this small 1D dataset, and with the model fitting quite well.  This is because it is the product of several probabilities, which are all quite small themselves.\n",
         "This will get out of hand pretty quickly with real datasets -- the likelihood will get so small that we can't represent it with normal finite-precision math\n",
         "\n",
         "This is why we use negative log likelihood"
@@ -326,7 +326,7 @@
         "beta_0, omega_0, beta_1, omega_1 = get_parameters()\n",
         "# Use our neural network to predict the mean of the Gaussian\n",
         "mu_pred = shallow_nn(x_train, beta_0, omega_0, beta_1, omega_1)\n",
-        "# Set the standard devation to something reasonable\n",
+        "# Set the standard deviation to something reasonable\n",
         "sigma = 0.2\n",
         "# Compute the log likelihood\n",
         "nll = compute_negative_log_likelihood(y_train, mu_pred, sigma)\n",
@@ -397,7 +397,7 @@
       "source": [
         "# Define a range of values for the parameter\n",
         "beta_1_vals = np.arange(0,1.0,0.01)\n",
-        "# Create some arrays to store the likelihoods, negative log likehoos and sum of squares\n",
+        "# Create some arrays to store the likelihoods, negative log likelihoods and sum of squares\n",
         "likelihoods = np.zeros_like(beta_1_vals)\n",
         "nlls = np.zeros_like(beta_1_vals)\n",
         "sum_squares = np.zeros_like(beta_1_vals)\n",
@@ -482,7 +482,7 @@
       "source": [
         "# Define a range of values for the parameter\n",
         "sigma_vals = np.arange(0.1,0.5,0.005)\n",
-        "# Create some arrays to store the likelihoods, negative log likehoos and sum of squares\n",
+        "# Create some arrays to store the likelihoods, negative log likelihoods and sum of squares\n",
         "likelihoods = np.zeros_like(sigma_vals)\n",
         "nlls = np.zeros_like(sigma_vals)\n",
         "sum_squares = np.zeros_like(sigma_vals)\n",

CM20315/CM20315_Loss_II.ipynb

@@ -34,7 +34,7 @@
         "\n",
         "This practical investigates loss functions.  In part I we investigated univariate regression (where the output data $y$ is continuous.  Our formulation was based on the normal/Gaussian distribution.\n",
         "\n",
-        "In this notebook, we investigate binary classification (where the output data is 0 or 1).  This will be based on the Bernouilli distribution\n",
+        "In this notebook, we investigate binary classification (where the output data is 0 or 1).  This will be based on the Bernoulli distribution\n",
         "\n",
         "In part III we'll investigate multiclass classification (where the outputs data can take multiple values 1,... K.\n",
         "\n",
@@ -199,7 +199,7 @@
     {
       "cell_type": "markdown",
       "source": [
-        "The left is model output and the right is the model output after the sigmoid has been applied, so it now lies in the range [0,1] and represents the probabiilty, that y=1.  The black dots show the training data.  We'll compute the the likelihood and the negative log likelihood."
+        "The left is model output and the right is the model output after the sigmoid has been applied, so it now lies in the range [0,1] and represents the probability, that y=1.  The black dots show the training data.  We'll compute the the likelihood and the negative log likelihood."
       ],
       "metadata": {
         "id": "MvVX6tl9AEXF"
@@ -210,7 +210,7 @@
       "source": [
         "# Return probability under Bernoulli distribution for input x\n",
         "def bernoulli_distribution(y, lambda_param):\n",
-        "    # TODO-- write in the equation for the Bernoullid distribution \n",
+        "    # TODO-- write in the equation for the Bernoulli distribution \n",
         "    # Equation 5.17 from the notes (you will need np.power)\n",
         "    # Replace the line below\n",
         "    prob = np.zeros_like(y)\n",
@@ -249,7 +249,7 @@
       "source": [
         "# Return the likelihood of all of the data under the model\n",
         "def compute_likelihood(y_train, lambda_param):\n",
-        "  # TODO -- compute the likelihood of the data -- the product of the Bernoullis probabilities for each data point\n",
+        "  # TODO -- compute the likelihood of the data -- the product of the Bernoulli's probabilities for each data point\n",
         "  # Top line of equation 5.3 in the notes\n",
         "  # You will need np.prod() and the bernoulli_distribution function you used above\n",
         "  # Replace the line below\n",
@@ -284,7 +284,7 @@
     {
       "cell_type": "markdown",
       "source": [
-        "You can see that this gives a very small answer, even for this small 1D dataset, and with the model fitting quite well.  This is because it is the product of sveral probabilities, which are all quite small themselves.\n",
+        "You can see that this gives a very small answer, even for this small 1D dataset, and with the model fitting quite well.  This is because it is the product of several probabilities, which are all quite small themselves.\n",
         "This will get out of hand pretty quickly with real datasets -- the likelihood will get so small that we can't represent it with normal finite-precision math\n",
         "\n",
         "This is why we use negative log likelihood"
@@ -317,7 +317,7 @@
         "beta_0, omega_0, beta_1, omega_1 = get_parameters()\n",
         "# Use our neural network to predict the mean of the Gaussian\n",
         "model_out = shallow_nn(x_train, beta_0, omega_0, beta_1, omega_1)\n",
-        "# Set the standard devation to something reasonable\n",
+        "# Set the standard deviation to something reasonable\n",
         "lambda_train = sigmoid(model_out)\n",
         "# Compute the log likelihood\n",
         "nll = compute_negative_log_likelihood(y_train, lambda_train)\n",
@@ -362,7 +362,7 @@
       "source": [
         "# Define a range of values for the parameter\n",
         "beta_1_vals = np.arange(-2,6.0,0.1)\n",
-        "# Create some arrays to store the likelihoods, negative log likehoods\n",
+        "# Create some arrays to store the likelihoods, negative log likelihoods\n",
         "likelihoods = np.zeros_like(beta_1_vals)\n",
         "nlls = np.zeros_like(beta_1_vals)\n",
         "\n",

CM20315/CM20315_Loss_III.ipynb

@@ -33,7 +33,7 @@
         "# Loss functions part III\n",
         "\n",
         "This practical investigates loss functions.  In part I we investigated univariate regression (where the output data $y$ is continuous.  Our formulation was based on the normal/Gaussian distribution.\n",
-        "In part II we investigated binary classification (where the output data is 0 or 1).  This will be based on the Bernouilli distribution.<br><br>\n",
+        "In part II we investigated binary classification (where the output data is 0 or 1).  This will be based on the Bernoulli distribution.<br><br>\n",
         "\n",
         "Now we'll investigate multiclass classification (where the outputs data can take multiple values 1,... K, which is based on the categorical distribution\n",
         "\n",
@@ -218,7 +218,7 @@
     {
       "cell_type": "markdown",
       "source": [
-        "The left is model output and the right is the model output after the softmax has been applied, so it now lies in the range [0,1] and represents the probabiilty, that y=0 (red), 1 (green) and 2 (blue)   The dots at the bottom show the training data with the same color scheme.  So we want the red curve to be high where there are red dots, the green curve to be high where there are green dotsmand the blue curve to be high where there are blue dots  We'll compute the the likelihood and the negative log likelihood."
+        "The left is model output and the right is the model output after the softmax has been applied, so it now lies in the range [0,1] and represents the probability, that y=0 (red), 1 (green) and 2 (blue)   The dots at the bottom show the training data with the same color scheme.  So we want the red curve to be high where there are red dots, the green curve to be high where there are green dotsmand the blue curve to be high where there are blue dots  We'll compute the the likelihood and the negative log likelihood."
       ],
       "metadata": {
         "id": "MvVX6tl9AEXF"
@@ -228,7 +228,7 @@
       "cell_type": "code",
       "source": [
         "# Return probability under Bernoulli distribution for input x\n",
-        "# Complicated code to commpute it but just take value from row k of lambda param where y =k, \n",
+        "# Complicated code to compute it but just take value from row k of lambda param where y =k, \n",
         "def categorical_distribution(y, lambda_param):\n",
         "    prob = np.zeros_like(y)\n",
         "    for row_index in range(lambda_param.shape[0]):\n",
@@ -305,7 +305,7 @@
     {
       "cell_type": "markdown",
       "source": [
-        "You can see that this gives a very small answer, even for this small 1D dataset, and with the model fitting quite well.  This is because it is the product of sveral probabilities, which are all quite small themselves.\n",
+        "You can see that this gives a very small answer, even for this small 1D dataset, and with the model fitting quite well.  This is because it is the product of several probabilities, which are all quite small themselves.\n",
         "This will get out of hand pretty quickly with real datasets -- the likelihood will get so small that we can't represent it with normal finite-precision math\n",
         "\n",
         "This is why we use negative log likelihood"
@@ -338,7 +338,7 @@
         "beta_0, omega_0, beta_1, omega_1 = get_parameters()\n",
         "# Use our neural network to predict the mean of the Gaussian\n",
         "model_out = shallow_nn(x_train, beta_0, omega_0, beta_1, omega_1)\n",
-        "# Set the standard devation to something reasonable\n",
+        "# Set the standard deviation to something reasonable\n",
         "lambda_train = softmax(model_out)\n",
         "# Compute the log likelihood\n",
         "nll = compute_negative_log_likelihood(y_train, lambda_train)\n",
@@ -365,7 +365,7 @@
       "source": [
         "# Define a range of values for the parameter\n",
         "beta_1_vals = np.arange(-2,6.0,0.1)\n",
-        "# Create some arrays to store the likelihoods, negative log likehoods\n",
+        "# Create some arrays to store the likelihoods, negative log likelihoods\n",
         "likelihoods = np.zeros_like(beta_1_vals)\n",
         "nlls = np.zeros_like(beta_1_vals)\n",
         "\n",

CM20315/CM20315_Shallow.ipynb

@@ -233,7 +233,7 @@
         "# TODO\n",
         "# 1. Predict what effect changing phi_0 will have on the network.  \n",
         "#   Answer:\n",
-        "# 2. Predict what effect multplying phi_1, phi_2, phi_3 by 0.5 would have.  Check if you are correct\n",
+        "# 2. Predict what effect multiplying phi_1, phi_2, phi_3 by 0.5 would have.  Check if you are correct\n",
         "#   Answer:\n",
         "# 3. Predict what effect multiplying phi_1 by -1 will have.  Check if you are correct.\n",
         "#   Answer:\n",
@@ -500,7 +500,7 @@
         "print(\"Loss = %3.3f\"%(loss))\n",
         "\n",
         "# TODO.  Manipulate the parameters (by hand!) to make the function \n",
-        "# fit the data better and try to reduct the loss to as small a number \n",
+        "# fit the data better and try to reduce the loss to as small a number \n",
         "# as possible.  The best that I could do was 0.181\n",
         "# Tip... start by manipulating phi_0.\n",
         "# It's not that easy, so don't spend too much time on this!"

CM20315/CM20315_Training_I.ipynb

@@ -108,7 +108,7 @@
       "source": [
         "def line_search(loss_function, thresh=.0001, max_iter = 10, draw_flag = False):\n",
         "\n",
-        "    # Initialize four points along the rnage we are going to search\n",
+        "    # Initialize four points along the range we are going to search\n",
         "    a = 0\n",
         "    b = 0.33\n",
         "    c = 0.66\n",
@@ -139,7 +139,7 @@
         "        # Rule #2 If point b is less than point c then\n",
         "        #                     then point d becomes point c, and\n",
         "        #                     point b becomes 1/3 between a and new d\n",
-        "        #                     point c beocome 2/3 between a and new d \n",
+        "        #                     point c becomes 2/3 between a and new d \n",
         "        # TODO REPLACE THE BLOCK OF CODE BELOW WITH THIS RULE\n",
         "        if (0):\n",
         "          continue;\n",
@@ -147,7 +147,7 @@
         "        # Rule #3 If point c is less than point b then\n",
         "        #                     then point a becomes point b, and\n",
         "        #                     point b becomes 1/3 between new a and d\n",
-        "        #                     point c beocome 2/3 between new a and d \n",
+        "        #                     point c becomes 2/3 between new a and d \n",
         "        # TODO REPLACE THE BLOCK OF CODE BELOW WITH THIS RULE\n",
         "        if(0):\n",
         "          continue\n",

CM20315/CM20315_Training_II.ipynb

@@ -114,7 +114,7 @@
     {
       "cell_type": "code",
       "source": [
-        "# Initialize the parmaeters and draw the model\n",
+        "# Initialize the parameters and draw the model\n",
         "phi = np.zeros((2,1))\n",
         "phi[0] = 0.6      # Intercept\n",
         "phi[1] = -0.2      # Slope\n",
@@ -314,7 +314,7 @@
         "  return compute_loss(data[0,:], data[1,:], model, phi_start+ gradient * dist_prop)\n",
         "\n",
         "def line_search(data, model, phi, gradient, thresh=.00001, max_dist = 0.1, max_iter = 15, verbose=False):\n",
-        "    # Initialize four points along the rnage we are going to search\n",
+        "    # Initialize four points along the range we are going to search\n",
         "    a = 0\n",
         "    b = 0.33 * max_dist\n",
         "    c = 0.66 * max_dist\n",
@@ -345,7 +345,7 @@
         "        # Rule #2 If point b is less than point c then\n",
         "        #                     then point d becomes point c, and\n",
         "        #                     point b becomes 1/3 between a and new d\n",
-        "        #                     point c beocome 2/3 between a and new d \n",
+        "        #                     point c becomes 2/3 between a and new d \n",
         "        if lossb < lossc:\n",
         "          d = c\n",
         "          b = a+ (d-a)/3\n",
@@ -355,7 +355,7 @@
         "        # Rule #2 If point c is less than point b then\n",
         "        #                     then point a becomes point b, and\n",
         "        #                     point b becomes 1/3 between new a and d\n",
-        "        #                     point c beocome 2/3 between new a and d \n",
+        "        #                     point c becomes 2/3 between new a and d \n",
         "        a = b\n",
         "        b = a+ (d-a)/3\n",
         "        c = a+ 2*(d-a)/3\n",

CM20315/CM20315_Training_III.ipynb

@@ -340,7 +340,7 @@
         "  return compute_loss(data[0,:], data[1,:], model, phi_start+ gradient * dist_prop)\n",
         "\n",
         "def line_search(data, model, phi, gradient, thresh=.00001, max_dist = 0.1, max_iter = 15, verbose=False):\n",
-        "    # Initialize four points along the rnage we are going to search\n",
+        "    # Initialize four points along the range we are going to search\n",
         "    a = 0\n",
         "    b = 0.33 * max_dist\n",
         "    c = 0.66 * max_dist\n",
@@ -371,7 +371,7 @@
         "        # Rule #2 If point b is less than point c then\n",
         "        #                     then point d becomes point c, and\n",
         "        #                     point b becomes 1/3 between a and new d\n",
-        "        #                     point c beocome 2/3 between a and new d \n",
+        "        #                     point c becomes 2/3 between a and new d \n",
         "        if lossb < lossc:\n",
         "          d = c\n",
         "          b = a+ (d-a)/3\n",
@@ -381,7 +381,7 @@
         "        # Rule #2 If point c is less than point b then\n",
         "        #                     then point a becomes point b, and\n",
         "        #                     point b becomes 1/3 between new a and d\n",
-        "        #                     point c beocome 2/3 between new a and d \n",
+        "        #                     point c becomes 2/3 between new a and d \n",
         "        a = b\n",
         "        b = a+ (d-a)/3\n",
         "        c = a+ 2*(d-a)/3\n",

CM20315/CM20315_Transformers.ipynb

@@ -175,7 +175,7 @@
     {
       "cell_type": "code",
       "source": [
-        "# TODO Modify the code below by changeing the number of tokens generated and the initial sentence\n",
+        "# TODO Modify the code below by changing the number of tokens generated and the initial sentence\n",
         "# to get a feel for how well this works.  Since I didn't reset the seed, it will give a different\n",
         "# answer every time that you run it.\n",
         "\n",
@@ -253,7 +253,7 @@
     {
       "cell_type": "code",
       "source": [
-        "# TODO Modify the code below by changeing the number of tokens generated and the initial sentence\n",
+        "# TODO Modify the code below by changing the number of tokens generated and the initial sentence\n",
         "# to get a feel for how well this works.  \n",
         "\n",
         "# TODO Experiment with changing this line:\n",
@@ -471,7 +471,7 @@
     {
       "cell_type": "code",
       "source": [
-        "# This routine reutnrs the k'th most likely next token.\n",
+        "# This routine returns the k'th most likely next token.\n",
         "# If k =0 then it returns the most likely token, if k=1 it returns the next most likely and so on\n",
         "# We will need this for beam search\n",
         "def get_kth_most_likely_token(input_tokens, model, tokenizer, k):\n",

CM20315_2023/CM20315_Coursework_I.ipynb

@@ -0,0 +1,280 @@
+{
+  "nbformat": 4,
+  "nbformat_minor": 0,
+  "metadata": {
+    "colab": {
+      "provenance": [],
+      "authorship_tag": "ABX9TyPNASgWoh4kBvxFP0xkN/I4",
+      "include_colab_link": true
+    },
+    "kernelspec": {
+      "name": "python3",
+      "display_name": "Python 3"
+    },
+    "language_info": {
+      "name": "python"
+    }
+  },
+  "cells": [
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "view-in-github",
+        "colab_type": "text"
+      },
+      "source": [
+        "<a href=\"https://colab.research.google.com/github/udlbook/udlbook/blob/main/CM20315_2023/CM20315_Coursework_I.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "# Coursework I -- Model hyperparameters\n",
+        "\n",
+        "The goal of the coursework is to modify a simple bit of numpy code that trains a network and measures the performance on a validation set for the MNIST 1D dataset.\n",
+        "\n",
+        "In this coursework, you need to modify the **model hyperparameters** (only) to improve the performance over the current attempt.  This could mean the number of layers, the number of hidden units per layer, or the type of activation function, or any combination of the three.\n",
+        "\n",
+        "The only constraint is that you MUST use a fully connected network (no convolutional networks for now if you have read ahead in the book).\n",
+        "\n",
+        "You must improve the performance by at least 2% to get full marks.\n",
+        "\n",
+        "You will need to upload three things to Moodle:\n",
+        "1.   The image that this notebook saves (click the folder icon on the left on colab to download it)\n",
+        "2.   The lines of code you changed\n",
+        "3.   The whole notebook as a .ipynb file.  You can do this on the File menu\n",
+        "\n",
+        "\n"
+      ],
+      "metadata": {
+        "id": "t9vk9Elugvmi"
+      }
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "import numpy as np\n",
+        "import os\n",
+        "import torch, torch.nn as nn\n",
+        "from torch.utils.data import TensorDataset, DataLoader\n",
+        "from torch.optim.lr_scheduler import StepLR\n",
+        "import matplotlib.pyplot as plt\n",
+        "import random\n",
+        "import gdown"
+      ],
+      "metadata": {
+        "id": "YrXWAH7sUWvU"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "\n",
+        "# Run this once to copy the train and validation data to your CoLab environment\n",
+        "# or download from my github to your local machine if you are doing this locally\n",
+        "if not os.path.exists('./Data.zip'):\n",
+        "  !gdown 1HtnCrncY6dFCYqzgPf1HtPVAerTpwFRm\n",
+        "  !unzip Data.zip"
+      ],
+      "metadata": {
+        "id": "wScBGXXFVadm"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "# Load in the data\n",
+        "train_data_x = np.load('train_data_x.npy')\n",
+        "val_data_y = np.load('val_data_y.npy')\n",
+        "train_data_y = np.load('train_data_y.npy')\n",
+        "val_data_x = np.load('val_data_x.npy')\n",
+        "# Print out sizes\n",
+        "print(\"Train data: %d examples (columns), each of which has %d dimensions (rows)\"%((train_data_x.shape[1],train_data_x.shape[0])))\n",
+        "print(\"Validation data: %d examples (columns), each of which has %d dimensions (rows)\"%((val_data_x.shape[1],val_data_x.shape[0])))"
+      ],
+      "metadata": {
+        "id": "8bKADvLHbiV5"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "Define the network"
+      ],
+      "metadata": {
+        "id": "_sFvRDGrl4qe"
+      }
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "# YOU SHOULD ONLY CHANGE THIS CELL!\n",
+        "\n",
+        "# There are 40 input dimensions and 10 output dimensions for this data\n",
+        "# The inputs correspond to the 40 offsets in the MNIST1D template.\n",
+        "D_i = 40\n",
+        "# The outputs correspond to the 10 digits\n",
+        "D_o = 10\n",
+        "\n",
+        "# Number of hidden units in layers 1 and 2\n",
+        "D_1 = 100\n",
+        "D_2 = 100\n",
+        "\n",
+        "# create model with two hidden layers\n",
+        "model = nn.Sequential(\n",
+        "nn.Linear(D_i, D_1),\n",
+        "nn.ReLU(),\n",
+        "nn.Linear(D_1, D_2),\n",
+        "nn.ReLU(),\n",
+        "nn.Linear(D_2, D_o))"
+      ],
+      "metadata": {
+        "id": "FslroPJJffrh"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "# He initialization of weights\n",
+        "def weights_init(layer_in):\n",
+        "  if isinstance(layer_in, nn.Linear):\n",
+        "    nn.init.kaiming_uniform_(layer_in.weight)\n",
+        "    layer_in.bias.data.fill_(0.0)"
+      ],
+      "metadata": {
+        "id": "YgLaex1pfhqz"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "# You need all this stuff to ensure that PyTorch is deterministic\n",
+        "def set_seed(seed):\n",
+        "    torch.manual_seed(seed)\n",
+        "    torch.cuda.manual_seed_all(seed)\n",
+        "    torch.backends.cudnn.deterministic = True\n",
+        "    torch.backends.cudnn.benchmark = False\n",
+        "    np.random.seed(seed)\n",
+        "    random.seed(seed)\n",
+        "    os.environ['PYTHONHASHSEED'] = str(seed)"
+      ],
+      "metadata": {
+        "id": "zXRmxCQNnL_M"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "# Set seed so always get same result (do not change)\n",
+        "set_seed(1)\n",
+        "\n",
+        "# choose cross entropy loss function (equation 5.24 in the loss notes)\n",
+        "loss_function = nn.CrossEntropyLoss()\n",
+        "# construct SGD optimizer and initialize learning rate and momentum\n",
+        "optimizer = torch.optim.SGD(model.parameters(), lr = 0.05, momentum=0.9)\n",
+        "# object that decreases learning rate by half every 10 epochs\n",
+        "scheduler = StepLR(optimizer, step_size=10, gamma=0.5)\n",
+        "# create 100 dummy data points and store in data loader class\n",
+        "x_train = torch.tensor(train_data_x.transpose().astype('float32'))\n",
+        "y_train = torch.tensor(train_data_y.astype('long'))\n",
+        "x_val= torch.tensor(val_data_x.transpose().astype('float32'))\n",
+        "y_val = torch.tensor(val_data_y.astype('long'))\n",
+        "\n",
+        "# load the data into a class that creates the batches\n",
+        "data_loader = DataLoader(TensorDataset(x_train,y_train), batch_size=100, shuffle=True, worker_init_fn=np.random.seed(1))\n",
+        "\n",
+        "# Initialize model weights\n",
+        "model.apply(weights_init)\n",
+        "\n",
+        "# loop over the dataset n_epoch times\n",
+        "n_epoch = 50\n",
+        "# store the loss and the % correct at each epoch\n",
+        "losses_train = np.zeros((n_epoch))\n",
+        "errors_train = np.zeros((n_epoch))\n",
+        "losses_val = np.zeros((n_epoch))\n",
+        "errors_val = np.zeros((n_epoch))\n",
+        "\n",
+        "for epoch in range(n_epoch):\n",
+        "  # loop over batches\n",
+        "  for i, data in enumerate(data_loader):\n",
+        "    # retrieve inputs and labels for this batch\n",
+        "    x_batch, y_batch = data\n",
+        "    # zero the parameter gradients\n",
+        "    optimizer.zero_grad()\n",
+        "    # forward pass -- calculate model output\n",
+        "    pred = model(x_batch)\n",
+        "    # compute the lss\n",
+        "    loss = loss_function(pred, y_batch)\n",
+        "    # backward pass\n",
+        "    loss.backward()\n",
+        "    # SGD update\n",
+        "    optimizer.step()\n",
+        "\n",
+        "  # Run whole dataset to get statistics -- normally wouldn't do this\n",
+        "  pred_train = model(x_train)\n",
+        "  pred_val = model(x_val)\n",
+        "  _, predicted_train_class = torch.max(pred_train.data, 1)\n",
+        "  _, predicted_val_class = torch.max(pred_val.data, 1)\n",
+        "  errors_train[epoch] = 100 - 100 * (predicted_train_class == y_train).float().sum() / len(y_train)\n",
+        "  errors_val[epoch]= 100 - 100 * (predicted_val_class == y_val).float().sum() / len(y_val)\n",
+        "  losses_train[epoch] = loss_function(pred_train, y_train).item()\n",
+        "  losses_val[epoch]= loss_function(pred_val, y_val).item()\n",
+        "  print(f'Epoch {epoch:5d}, train loss {losses_train[epoch]:.6f}, train error {errors_train[epoch]:3.2f},  val loss {losses_val[epoch]:.6f}, percent error {errors_val[epoch]:3.2f}')\n",
+        "\n",
+        "  # tell scheduler to consider updating learning rate\n",
+        "  scheduler.step()\n",
+        "\n",
+        "# Plot the results\n",
+        "fig, ax = plt.subplots()\n",
+        "ax.plot(errors_train,'r-',label='train')\n",
+        "ax.plot(errors_val,'b-',label='validation')\n",
+        "ax.set_ylim(0,100); ax.set_xlim(0,n_epoch)\n",
+        "ax.set_xlabel('Epoch'); ax.set_ylabel('Error')\n",
+        "ax.set_title('Part I: Validation Result %3.2f'%(errors_val[-1]))\n",
+        "ax.legend()\n",
+        "ax.plot([0,n_epoch],[37.45, 37.45],'k:') # Original results. You should be better than this!\n",
+        "plt.savefig('Coursework_I_Results.png',format='png')\n",
+        "plt.show()"
+      ],
+      "metadata": {
+        "id": "NYw8I_3mmX5c"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "# Leave this all commented for now\n",
+        "# We'll see how well you did on the test data after the coursework is submitted\n",
+        "\n",
+        "# # I haven't given you this yet, leave commented\n",
+        "# test_data_x = np.load('test_data_x.npy')\n",
+        "# test_data_y = np.load('test_data_y.npy')\n",
+        "# x_test = torch.tensor(test_data_x.transpose().astype('float32'))\n",
+        "# y_test = torch.tensor(test_data_y.astype('long'))\n",
+        "# pred_test = model(x_test)\n",
+        "# _, predicted_test_class = torch.max(pred_test.data, 1)\n",
+        "# errors_test = 100 - 100 * (predicted_test_class == y_test).float().sum() / len(y_test)\n",
+        "# print(\"Test error = %3.3f\"%(errors_test))"
+      ],
+      "metadata": {
+        "id": "O7nBz-R84QdJ"
+      },
+      "execution_count": null,
+      "outputs": []
+    }
+  ]
+}

CM20315_2023/CM20315_Coursework_II.ipynb

@@ -0,0 +1,276 @@
+{
+  "nbformat": 4,
+  "nbformat_minor": 0,
+  "metadata": {
+    "colab": {
+      "provenance": [],
+      "authorship_tag": "ABX9TyM+iKos5DEoHUxL8+9oxA2A",
+      "include_colab_link": true
+    },
+    "kernelspec": {
+      "name": "python3",
+      "display_name": "Python 3"
+    },
+    "language_info": {
+      "name": "python"
+    }
+  },
+  "cells": [
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "view-in-github",
+        "colab_type": "text"
+      },
+      "source": [
+        "<a href=\"https://colab.research.google.com/github/udlbook/udlbook/blob/main/CM20315_2023/CM20315_Coursework_II.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "# Coursework II -- Training hyperparameters\n",
+        "\n",
+        "The goal of the coursework is to modify a simple bit of numpy code that trains a network and measures the performance on a validation set for the MNist 1D dataset.\n",
+        "\n",
+        "In this coursework, you need to modify the **training hyperparameters** (only) to improve the performance over the current attempt. This could mean the training algorithm, learning rate, learning rate schedule, momentum term, initialization etc.  \n",
+        "\n",
+        "You must improve the performance by at least 2% to get full marks.\n",
+        "\n",
+        "You will need to upload three things to Moodle:\n",
+        "1.   The image that this notebook saves (click the folder icon on the left on colab to download it)\n",
+        "2.   The lines of code you changed\n",
+        "3.   The whole notebook as a .ipynb file.  You can do this on the File menu"
+      ],
+      "metadata": {
+        "id": "t9vk9Elugvmi"
+      }
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "import numpy as np\n",
+        "import os\n",
+        "import torch, torch.nn as nn\n",
+        "from torch.utils.data import TensorDataset, DataLoader\n",
+        "from torch.optim.lr_scheduler import StepLR\n",
+        "import matplotlib.pyplot as plt\n",
+        "import random\n",
+        "import gdown"
+      ],
+      "metadata": {
+        "id": "YrXWAH7sUWvU"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "# Run this once to copy the train and validation data to your CoLab environment\n",
+        "if not os.path.exists('./Data.zip'):\n",
+        "  !gdown 1HtnCrncY6dFCYqzgPf1HtPVAerTpwFRm\n",
+        "  !unzip Data.zip"
+      ],
+      "metadata": {
+        "id": "wScBGXXFVadm"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "# Load in the data\n",
+        "train_data_x = np.load('train_data_x.npy',allow_pickle=True)\n",
+        "train_data_y = np.load('train_data_y.npy',allow_pickle=True)\n",
+        "val_data_x = np.load('val_data_x.npy',allow_pickle=True)\n",
+        "val_data_y = np.load('val_data_y.npy',allow_pickle=True)\n",
+        "# Print out sizes\n",
+        "print(\"Train data: %d examples (columns), each of which has %d dimensions (rows)\"%((train_data_x.shape[1],train_data_x.shape[0])))\n",
+        "print(\"Validation data: %d examples (columns), each of which has %d dimensions (rows)\"%((val_data_x.shape[1],val_data_x.shape[0])))"
+      ],
+      "metadata": {
+        "id": "8bKADvLHbiV5"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "Define the network"
+      ],
+      "metadata": {
+        "id": "_sFvRDGrl4qe"
+      }
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "# YOU SHOULD NOT CHANGE THIS CELL!\n",
+        "\n",
+        "# There are 40 input dimensions and 10 output dimensions for this data\n",
+        "# The inputs correspond to the 40 offsets in the MNIST1D template.\n",
+        "D_i = 40\n",
+        "# The outputs correspond to the 10 digits\n",
+        "D_o = 10\n",
+        "\n",
+        "# Number of hidden units in layers 1 and 2\n",
+        "D_1 = 100\n",
+        "D_2 = 100\n",
+        "\n",
+        "# create model with two hidden layers\n",
+        "model = nn.Sequential(\n",
+        "nn.Linear(D_i, D_1),\n",
+        "nn.ReLU(),\n",
+        "nn.Linear(D_1, D_2),\n",
+        "nn.ReLU(),\n",
+        "nn.Linear(D_2, D_o))"
+      ],
+      "metadata": {
+        "id": "FslroPJJffrh"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "# He initialization of weights\n",
+        "def weights_init(layer_in):\n",
+        "  if isinstance(layer_in, nn.Linear):\n",
+        "    nn.init.kaiming_uniform_(layer_in.weight)\n",
+        "    layer_in.bias.data.fill_(0.0)"
+      ],
+      "metadata": {
+        "id": "YgLaex1pfhqz"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "# You need all this stuff to ensure that PyTorch is deterministic\n",
+        "def set_seed(seed):\n",
+        "    torch.manual_seed(seed)\n",
+        "    torch.cuda.manual_seed_all(seed)\n",
+        "    torch.backends.cudnn.deterministic = True\n",
+        "    torch.backends.cudnn.benchmark = False\n",
+        "    np.random.seed(seed)\n",
+        "    random.seed(seed)\n",
+        "    os.environ['PYTHONHASHSEED'] = str(seed)"
+      ],
+      "metadata": {
+        "id": "zXRmxCQNnL_M"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "# Set seed so always get same result (do not change)\n",
+        "set_seed(1)\n",
+        "\n",
+        "# choose cross entropy loss function (equation 5.24 in the loss notes)\n",
+        "loss_function = nn.CrossEntropyLoss()\n",
+        "# construct SGD optimizer and initialize learning rate and momentum\n",
+        "optimizer = torch.optim.SGD(model.parameters(), lr = 0.05, momentum=0.9)\n",
+        "# object that decreases learning rate by half every 10 epochs\n",
+        "scheduler = StepLR(optimizer, step_size=10, gamma=0.5)\n",
+        "# create 100 dummy data points and store in data loader class\n",
+        "x_train = torch.tensor(train_data_x.transpose().astype('float32'))\n",
+        "print(x_train.shape)\n",
+        "y_train = torch.tensor(train_data_y.astype('long'))\n",
+        "print(y_train.shape)\n",
+        "x_val= torch.tensor(val_data_x.transpose().astype('float32'))\n",
+        "y_val = torch.tensor(val_data_y.astype('long'))\n",
+        "\n",
+        "# load the data into a class that creates the batches\n",
+        "data_loader = DataLoader(TensorDataset(x_train,y_train), batch_size=100, shuffle=True, worker_init_fn=np.random.seed(1))\n",
+        "\n",
+        "# Initialize model weights\n",
+        "model.apply(weights_init)\n",
+        "\n",
+        "# loop over the dataset n_epoch times\n",
+        "n_epoch = 50\n",
+        "# store the loss and the % correct at each epoch\n",
+        "losses_train = np.zeros((n_epoch))\n",
+        "errors_train = np.zeros((n_epoch))\n",
+        "losses_val = np.zeros((n_epoch))\n",
+        "errors_val = np.zeros((n_epoch))\n",
+        "\n",
+        "for epoch in range(n_epoch):\n",
+        "  # loop over batches\n",
+        "  for i, data in enumerate(data_loader):\n",
+        "    # retrieve inputs and labels for this batch\n",
+        "    x_batch, y_batch = data\n",
+        "    # zero the parameter gradients\n",
+        "    optimizer.zero_grad()\n",
+        "    # forward pass -- calculate model output\n",
+        "    pred = model(x_batch)\n",
+        "    # compute the lss\n",
+        "    loss = loss_function(pred, y_batch)\n",
+        "    # backward pass\n",
+        "    loss.backward()\n",
+        "    # SGD update\n",
+        "    optimizer.step()\n",
+        "\n",
+        "  # Run whole dataset to get statistics -- normally wouldn't do this\n",
+        "  pred_train = model(x_train)\n",
+        "  pred_val = model(x_val)\n",
+        "  _, predicted_train_class = torch.max(pred_train.data, 1)\n",
+        "  _, predicted_val_class = torch.max(pred_val.data, 1)\n",
+        "  errors_train[epoch] = 100 - 100 * (predicted_train_class == y_train).float().sum() / len(y_train)\n",
+        "  errors_val[epoch]= 100 - 100 * (predicted_val_class == y_val).float().sum() / len(y_val)\n",
+        "  losses_train[epoch] = loss_function(pred_train, y_train).item()\n",
+        "  losses_val[epoch]= loss_function(pred_val, y_val).item()\n",
+        "  print(f'Epoch {epoch:5d}, train loss {losses_train[epoch]:.6f}, train error {errors_train[epoch]:3.2f},  val loss {losses_val[epoch]:.6f}, percent error {errors_val[epoch]:3.2f}')\n",
+        "\n",
+        "  # tell scheduler to consider updating learning rate\n",
+        "  scheduler.step()\n",
+        "\n",
+        "# Plot the results\n",
+        "fig, ax = plt.subplots()\n",
+        "ax.plot(errors_train,'r-',label='train')\n",
+        "ax.plot(errors_val,'b-',label='validation')\n",
+        "ax.set_ylim(0,100); ax.set_xlim(0,n_epoch)\n",
+        "ax.set_xlabel('Epoch'); ax.set_ylabel('Error')\n",
+        "ax.set_title('Part II: Validation Result %3.2f'%(errors_val[-1]))\n",
+        "ax.legend()\n",
+        "ax.plot([0,n_epoch],[37.45, 37.45],'k:') # Original results. You should be better than this!\n",
+        "plt.savefig('Coursework_II_Results.png',format='png')\n",
+        "plt.show()"
+      ],
+      "metadata": {
+        "id": "NYw8I_3mmX5c"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "# Leave this all commented for now\n",
+        "# We'll see how well you did on the test data after the coursework is submitted\n",
+        "\n",
+        "# # I haven't given you this yet, leave commented\n",
+        "# test_data_x = np.load('test_data_x.npy')\n",
+        "# test_data_y = np.load('test_data_y.npy')\n",
+        "# x_test = torch.tensor(test_data_x.transpose().astype('float32'))\n",
+        "# y_test = torch.tensor(test_data_y.astype('long'))\n",
+        "# pred_test = model(x_test)\n",
+        "# _, predicted_test_class = torch.max(pred_test.data, 1)\n",
+        "# errors_test = 100 - 100 * (predicted_test_class == y_test).float().sum() / len(y_test)\n",
+        "# print(\"Test error = %3.3f\"%(errors_test))"
+      ],
+      "metadata": {
+        "id": "O7nBz-R84QdJ"
+      },
+      "execution_count": null,
+      "outputs": []
+    }
+  ]
+}

CM20315_2023/CM20315_Coursework_III.ipynb

@@ -0,0 +1,275 @@
+{
+  "nbformat": 4,
+  "nbformat_minor": 0,
+  "metadata": {
+    "colab": {
+      "provenance": [],
+      "authorship_tag": "ABX9TyNDH1z3I76jjglu3o0LSlZc",
+      "include_colab_link": true
+    },
+    "kernelspec": {
+      "name": "python3",
+      "display_name": "Python 3"
+    },
+    "language_info": {
+      "name": "python"
+    }
+  },
+  "cells": [
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "view-in-github",
+        "colab_type": "text"
+      },
+      "source": [
+        "<a href=\"https://colab.research.google.com/github/udlbook/udlbook/blob/main/CM20315_2023/CM20315_Coursework_III.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "# Coursework III -- Regularization\n",
+        "\n",
+        "The goal of the coursework is to modify a simple bit of numpy code that trains a network and measures the performance on a validation set for the MNist 1D dataset.\n",
+        "\n",
+        "In this coursework, you need add **regularization** of some kind to improve the performance.  Anything from chapter 9 of the book or anything else you can find is fine *except* early stopping.  You must not change the model hyperparameters or the training algorithm.\n",
+        "\n",
+        "You must improve the performance by at least 2% to get full marks.\n",
+        "\n",
+        "You will need to upload three things to Moodle:\n",
+        "1.   The image that this notebook saves (click the folder icon on the left on colab to download it)\n",
+        "2.   The lines of code you changed\n",
+        "3.   The whole notebook as a .ipynb file.  You can do this on the File menu\n",
+        "\n",
+        "\n"
+      ],
+      "metadata": {
+        "id": "t9vk9Elugvmi"
+      }
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "import numpy as np\n",
+        "import os\n",
+        "import torch, torch.nn as nn\n",
+        "from torch.utils.data import TensorDataset, DataLoader\n",
+        "from torch.optim.lr_scheduler import StepLR\n",
+        "import matplotlib.pyplot as plt\n",
+        "import random\n",
+        "import gdown"
+      ],
+      "metadata": {
+        "id": "YrXWAH7sUWvU"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "# Run this once to copy the train and validation data to your CoLab environment\n",
+        "if not os.path.exists('./Data.zip'):\n",
+        "  !gdown 1HtnCrncY6dFCYqzgPf1HtPVAerTpwFRm\n",
+        "  !unzip Data.zip"
+      ],
+      "metadata": {
+        "id": "wScBGXXFVadm"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "# Load in the data\n",
+        "train_data_x = np.load('train_data_x.npy')\n",
+        "train_data_y = np.load('train_data_y.npy')\n",
+        "val_data_x = np.load('val_data_x.npy')\n",
+        "val_data_y = np.load('val_data_y.npy')\n",
+        "# Print out sizes\n",
+        "print(\"Train data: %d examples (columns), each of which has %d dimensions (rows)\"%((train_data_x.shape[1],train_data_x.shape[0])))\n",
+        "print(\"Validation data: %d examples (columns), each of which has %d dimensions (rows)\"%((val_data_x.shape[1],val_data_x.shape[0])))"
+      ],
+      "metadata": {
+        "id": "8bKADvLHbiV5"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "Define the network"
+      ],
+      "metadata": {
+        "id": "_sFvRDGrl4qe"
+      }
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "# There are 40 input dimensions and 10 output dimensions for this data\n",
+        "# The inputs correspond to the 40 offsets in the MNIST1D template.\n",
+        "D_i = 40\n",
+        "# The outputs correspond to the 10 digits\n",
+        "D_o = 10\n",
+        "\n",
+        "# Number of hidden units in layers 1 and 2\n",
+        "D_1 = 100\n",
+        "D_2 = 100\n",
+        "\n",
+        "# create model with two hidden layers\n",
+        "model = nn.Sequential(\n",
+        "nn.Linear(D_i, D_1),\n",
+        "nn.ReLU(),\n",
+        "nn.Linear(D_1, D_2),\n",
+        "nn.ReLU(),\n",
+        "nn.Linear(D_2, D_o))"
+      ],
+      "metadata": {
+        "id": "FslroPJJffrh"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "# He initialization of weights\n",
+        "def weights_init(layer_in):\n",
+        "  if isinstance(layer_in, nn.Linear):\n",
+        "    nn.init.kaiming_uniform_(layer_in.weight)\n",
+        "    layer_in.bias.data.fill_(0.0)"
+      ],
+      "metadata": {
+        "id": "YgLaex1pfhqz"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "# You need all this stuff to ensure that PyTorch is deterministic\n",
+        "def set_seed(seed):\n",
+        "    torch.manual_seed(seed)\n",
+        "    torch.cuda.manual_seed_all(seed)\n",
+        "    torch.backends.cudnn.deterministic = True\n",
+        "    torch.backends.cudnn.benchmark = False\n",
+        "    np.random.seed(seed)\n",
+        "    random.seed(seed)\n",
+        "    os.environ['PYTHONHASHSEED'] = str(seed)"
+      ],
+      "metadata": {
+        "id": "zXRmxCQNnL_M"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "# Set seed so always get same result (do not change)\n",
+        "set_seed(1)\n",
+        "\n",
+        "# choose cross entropy loss function (equation 5.24 in the loss notes)\n",
+        "loss_function = nn.CrossEntropyLoss()\n",
+        "# construct SGD optimizer and initialize learning rate and momentum\n",
+        "optimizer = torch.optim.SGD(model.parameters(), lr = 0.05, momentum=0.9)\n",
+        "# object that decreases learning rate by half every 10 epochs\n",
+        "scheduler = StepLR(optimizer, step_size=10, gamma=0.5)\n",
+        "# create 100 dummy data points and store in data loader class\n",
+        "x_train = torch.tensor(train_data_x.transpose().astype('float32'))\n",
+        "y_train = torch.tensor(train_data_y.astype('long'))\n",
+        "x_val= torch.tensor(val_data_x.transpose().astype('float32'))\n",
+        "y_val = torch.tensor(val_data_y.astype('long'))\n",
+        "\n",
+        "# load the data into a class that creates the batches\n",
+        "data_loader = DataLoader(TensorDataset(x_train,y_train), batch_size=100, shuffle=True, worker_init_fn=np.random.seed(1))\n",
+        "\n",
+        "# Initialize model weights\n",
+        "model.apply(weights_init)\n",
+        "\n",
+        "# loop over the dataset n_epoch times\n",
+        "n_epoch = 50\n",
+        "# store the loss and the % correct at each epoch\n",
+        "losses_train = np.zeros((n_epoch))\n",
+        "errors_train = np.zeros((n_epoch))\n",
+        "losses_val = np.zeros((n_epoch))\n",
+        "errors_val = np.zeros((n_epoch))\n",
+        "\n",
+        "for epoch in range(n_epoch):\n",
+        "  # loop over batches\n",
+        "  for i, data in enumerate(data_loader):\n",
+        "    # retrieve inputs and labels for this batch\n",
+        "    x_batch, y_batch = data\n",
+        "    # zero the parameter gradients\n",
+        "    optimizer.zero_grad()\n",
+        "    # forward pass -- calculate model output\n",
+        "    pred = model(x_batch)\n",
+        "    # compute the lss\n",
+        "    loss = loss_function(pred, y_batch)\n",
+        "    # backward pass\n",
+        "    loss.backward()\n",
+        "    # SGD update\n",
+        "    optimizer.step()\n",
+        "\n",
+        "  # Run whole dataset to get statistics -- normally wouldn't do this\n",
+        "  pred_train = model(x_train)\n",
+        "  pred_val = model(x_val)\n",
+        "  _, predicted_train_class = torch.max(pred_train.data, 1)\n",
+        "  _, predicted_val_class = torch.max(pred_val.data, 1)\n",
+        "  errors_train[epoch] = 100 - 100 * (predicted_train_class == y_train).float().sum() / len(y_train)\n",
+        "  errors_val[epoch]= 100 - 100 * (predicted_val_class == y_val).float().sum() / len(y_val)\n",
+        "  losses_train[epoch] = loss_function(pred_train, y_train).item()\n",
+        "  losses_val[epoch]= loss_function(pred_val, y_val).item()\n",
+        "  print(f'Epoch {epoch:5d}, train loss {losses_train[epoch]:.6f}, train error {errors_train[epoch]:3.2f},  val loss {losses_val[epoch]:.6f}, percent error {errors_val[epoch]:3.2f}')\n",
+        "\n",
+        "  # tell scheduler to consider updating learning rate\n",
+        "  scheduler.step()\n",
+        "\n",
+        "# Plot the results\n",
+        "fig, ax = plt.subplots()\n",
+        "ax.plot(errors_train,'r-',label='train')\n",
+        "ax.plot(errors_val,'b-',label='validation')\n",
+        "ax.set_ylim(0,100); ax.set_xlim(0,n_epoch)\n",
+        "ax.set_xlabel('Epoch'); ax.set_ylabel('Error')\n",
+        "ax.set_title('Part III: Validation Result %3.2f'%(errors_val[-1]))\n",
+        "ax.legend()\n",
+        "ax.plot([0,n_epoch],[37.45, 37.45],'k:') # Original results. You should be better than this!\n",
+        "plt.savefig('Coursework_III_Results.png',format='png')\n",
+        "plt.show()"
+      ],
+      "metadata": {
+        "id": "NYw8I_3mmX5c"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "# Leave this all commented for now\n",
+        "# We'll see how well you did on the test data after the coursework is submitted\n",
+        "\n",
+        "\n",
+        "# # I haven't given you this yet, leave commented\n",
+        "# test_data_x = np.load('test_data_x.npy')\n",
+        "# test_data_y = np.load('test_data_y.npy')\n",
+        "# x_test = torch.tensor(test_data_x.transpose().astype('float32'))\n",
+        "# y_test = torch.tensor(test_data_y.astype('long'))\n",
+        "# pred_test = model(x_test)\n",
+        "# _, predicted_test_class = torch.max(pred_test.data, 1)\n",
+        "# errors_test = 100 - 100 * (predicted_test_class == y_test).float().sum() / len(y_test)\n",
+        "# print(\"Test error = %3.3f\"%(errors_test))"
+      ],
+      "metadata": {
+        "id": "O7nBz-R84QdJ"
+      },
+      "execution_count": null,
+      "outputs": []
+    }
+  ]
+}

CM20315_2023/CM20315_Coursework_IV.ipynb

@@ -0,0 +1,212 @@
+{
+  "nbformat": 4,
+  "nbformat_minor": 0,
+  "metadata": {
+    "colab": {
+      "provenance": [],
+      "authorship_tag": "ABX9TyMrWYwQrwgJvDza1vhYK9WQ",
+      "include_colab_link": true
+    },
+    "kernelspec": {
+      "name": "python3",
+      "display_name": "Python 3"
+    },
+    "language_info": {
+      "name": "python"
+    }
+  },
+  "cells": [
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "view-in-github",
+        "colab_type": "text"
+      },
+      "source": [
+        "<a href=\"https://colab.research.google.com/github/udlbook/udlbook/blob/main/CM20315_2023/CM20315_Coursework_IV.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "# Coursework IV\n",
+        "\n",
+        "This coursework explores the geometry of high dimensional spaces.  It doesn't behave how you would expect and all your intuitions are wrong!  You will write code and it will give you three numerical answers that you need to type into Moodle."
+      ],
+      "metadata": {
+        "id": "EjLK-kA1KnYX"
+      }
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "4ESMmnkYEVAb"
+      },
+      "outputs": [],
+      "source": [
+        "import numpy as np\n",
+        "import matplotlib.pyplot as plt\n",
+        "import scipy.special as sci"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "# Part (a)\n",
+        "\n",
+        "In part (a) of the practical, we investigate how close random points are in 2D, 100D, and 1000D.   In each case, we generate 1000 points and calculate the Euclidean distance between each pair.  You should find that in 1000D, the furthest two points are only slightly further apart than the nearest points.  Weird!"
+      ],
+      "metadata": {
+        "id": "MonbPEitLNgN"
+      }
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "# Fix the random seed so we all have the same random numbers\n",
+        "np.random.seed(0)\n",
+        "n_data = 1000\n",
+        "# Create 1000 data examples (columns) each with 2 dimensions (rows)\n",
+        "n_dim = 2\n",
+        "x_2D = np.random.normal(size=(n_dim,n_data))\n",
+        "# Create 1000 data examples (columns) each with 100 dimensions (rows)\n",
+        "n_dim = 100\n",
+        "x_100D = np.random.normal(size=(n_dim,n_data))\n",
+        "# Create 1000 data examples (columns) each with 1000 dimensions (rows)\n",
+        "n_dim = 1000\n",
+        "x_1000D = np.random.normal(size=(n_dim,n_data))\n",
+        "\n",
+        "# These values should be the same, otherwise your answer will be wrong\n",
+        "# Get in touch if they are not!\n",
+        "print('Sum of your data is %3.3f, Should be %3.3f'%(np.sum(x_1000D),1036.321))"
+      ],
+      "metadata": {
+        "id": "vZSHVmcWEk14"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "def distance_ratio(x):\n",
+        "  # TODO -- replace the two lines below to calculate the largest and smallest Euclidean distance between\n",
+        "  # the data points in the columns of x.  DO NOT include the distance between the data point\n",
+        "  # and itself (which is obviously zero)\n",
+        "  smallest_dist = 1.0\n",
+        "  largest_dist = 1.0\n",
+        "\n",
+        "  # Calculate the ratio and return\n",
+        "  dist_ratio = largest_dist / smallest_dist\n",
+        "  return dist_ratio"
+      ],
+      "metadata": {
+        "id": "PhVmnUs8ErD9"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "print('Ratio of largest to smallest distance 2D: %3.3f'%(distance_ratio(x_2D)))\n",
+        "print('Ratio of largest to smallest distance 100D: %3.3f'%(distance_ratio(x_100D)))\n",
+        "print('Ratio of largest to smallest distance 1000D: %3.3f'%(distance_ratio(x_1000D)))\n",
+        "print('**Note down the last of these three numbers, you will need to submit it for your coursework**')"
+      ],
+      "metadata": {
+        "id": "0NdPxfn5GQuJ"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "# Part (b)\n",
+        "\n",
+        "In part (b) of the practical we calculate the volume of a hypersphere of radius 0.5 (i.e., of diameter 1) as a function of the radius.  You will find that the volume decreases to almost nothing in high dimensions.  All of the volume is in the corners of the unit hypercube (which always has volume 1). Double weird.\n",
+        "\n",
+        "Note that you you can check your answer by doing the calculation for 2D using the standard formula for the area of a circle and making sure it matches."
+      ],
+      "metadata": {
+        "id": "b2FYKV1SL4Z7"
+      }
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "def volume_of_hypersphere(diameter, dimensions):\n",
+        "  # Formula given in Problem 8.7 of the notes\n",
+        "  # You will need sci.gamma()\n",
+        "  # Check out:    https://docs.scipy.org/doc/scipy/reference/generated/scipy.special.gamma.html\n",
+        "  # Also use this value for pi\n",
+        "  pi = np.pi\n",
+        "  # TODO replace this code with formula for the volume of a hypersphere\n",
+        "  volume = 1.0\n",
+        "\n",
+        "  return volume\n"
+      ],
+      "metadata": {
+        "id": "CZoNhD8XJaHR"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "diameter = 1.0\n",
+        "for c_dim in range(1,11):\n",
+        "  print(\"Volume of unit diameter hypersphere in %d dimensions is %3.3f\"%(c_dim, volume_of_hypersphere(diameter, c_dim)))\n",
+        "print('**Note down the last of these ten numbers, you will need to submit it for your coursework**')"
+      ],
+      "metadata": {
+        "id": "fNTBlg_GPEUh"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "# Part (c)\n",
+        "\n",
+        "In part (c) of the coursework, you will calculate what proportion of the volume of a hypersphere is in the outer 1% of the radius/diameter.  Calculate the volume of a hypersphere and then the volume of a hypersphere with 0.99 of the radius and then figure out the proportion (a number between 0 and 1).  You'll see that by the time we get to 300 dimensions most of the volume is in the outer 1 percent.  Extremely weird!"
+      ],
+      "metadata": {
+        "id": "GdyMeOBmoXyF"
+      }
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "def get_prop_of_volume_in_outer_1_percent(dimension):\n",
+        "  # TODO -- replace this line\n",
+        "  proportion = 1.0\n",
+        "\n",
+        "  return proportion"
+      ],
+      "metadata": {
+        "id": "8_CxZ2AIpQ8w"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "# While we're here, let's look at how much of the volume is in the outer 1% of the radius\n",
+        "for c_dim in [1,2,10,20,50,100,150,200,250,300]:\n",
+        "  print('Proportion of volume in outer 1 percent of radius in %d dimensions =%3.3f'%(c_dim, get_prop_of_volume_in_outer_1_percent(c_dim)))\n",
+        "print('**Note down the last of these ten numbers, you will need to submit it for your coursework**')"
+      ],
+      "metadata": {
+        "id": "LtMDIn2qPVfJ"
+      },
+      "execution_count": null,
+      "outputs": []
+    }
+  ]
+}

CM20315_2023/CM20315_Coursework_V_2023.ipynb

@@ -0,0 +1,525 @@
+{
+  "nbformat": 4,
+  "nbformat_minor": 0,
+  "metadata": {
+    "colab": {
+      "provenance": [],
+      "authorship_tag": "ABX9TyN7KaQQ63bf52r+b5as0MkK",
+      "include_colab_link": true
+    },
+    "kernelspec": {
+      "name": "python3",
+      "display_name": "Python 3"
+    },
+    "language_info": {
+      "name": "python"
+    }
+  },
+  "cells": [
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "view-in-github",
+        "colab_type": "text"
+      },
+      "source": [
+        "<a href=\"https://colab.research.google.com/github/udlbook/udlbook/blob/main/CM20315_2023/CM20315_Coursework_V_2023.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "# **Coursework V: Backpropagation in Toy Model**\n",
+        "\n",
+        "This notebook computes the derivatives of a toy function similar (but different from) that in section 7.3 of the book.\n",
+        "\n",
+        "Work through the cells below, running each cell in turn. In various places you will see the words \"TO DO\". Follow the instructions at these places and make predictions about what is going to happen or write code to complete the functions.  At various points, you will get an answer that you need to copy into Moodle to be marked.\n",
+        "\n",
+        "Post to the content forum if you find any mistakes or need to clarify something."
+      ],
+      "metadata": {
+        "id": "pOZ6Djz0dhoy"
+      }
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "# Problem setting\n",
+        "\n",
+        "We're going to investigate how to take the derivatives of functions where one operation is composed with another, which is composed with a third and so on.  For example, consider the model:\n",
+        "\n",
+        "\\begin{equation}\n",
+        "     \\mbox{f}[x,\\boldsymbol\\phi] = \\beta_3+\\omega_3\\cdot\\mbox{PReLU}\\Bigl[\\gamma, \\beta_2+\\omega_2\\cdot\\mbox{PReLU}\\bigl[\\gamma, \\beta_1+\\omega_1\\cdot\\mbox{PReLU}[\\gamma, \\beta_0+\\omega_0x]\\bigr]\\Bigr],\n",
+        "\\end{equation}\n",
+        "\n",
+        "with parameters $\\boldsymbol\\phi=\\{\\beta_0,\\omega_0,\\beta_1,\\omega_1,\\beta_2,\\omega_2,\\beta_3,\\omega_3\\}$, where\n",
+        "\n",
+        "\\begin{equation}\n",
+        "\\mbox{PReLU}[\\gamma, z] = \\begin{cases} \\gamma\\cdot z & \\quad z \\leq0 \\\\ z & \\quad z> 0\\end{cases}.\n",
+        "\\end{equation}\n",
+        "\n",
+        "Suppose that we have a binary cross-entropy loss function (equation 5.20 from the book):\n",
+        "\n",
+        "\\begin{equation*}\n",
+        "\\ell_i  = -(1-y_{i})\\log\\Bigl[1-\\mbox{sig}[\\mbox{f}[\\mathbf{x}_i,\\boldsymbol\\phi]]\\Bigr] - y_{i}\\log\\Bigl[\\mbox{sig}[\\mbox{f}[\\mathbf{x}_i,\\boldsymbol\\phi]]\\Bigr].\n",
+        "\\end{equation*}\n",
+        "\n",
+        "Assume that we know the current values of $\\beta_{0},\\beta_{1},\\beta_{2},\\beta_{3},\\omega_{0},\\omega_{1},\\omega_{2},\\omega_{3}$, $\\gamma$, $x_i$ and $y_i$. We want to know how $\\ell_i$ changes when we make a small change to $\\beta_{0},\\beta_{1},\\beta_{2},\\beta_{3},\\omega_{0},\\omega_{1},\\omega_{2}$, or $\\omega_{3}$.  In other words, we want to compute the eight derivatives:\n",
+        "\n",
+        "\\begin{eqnarray*}\n",
+        "\\frac{\\partial \\ell_i}{\\partial \\beta_{0}}, \\quad \\frac{\\partial \\ell_i}{\\partial \\beta_{1}}, \\quad \\frac{\\partial \\ell_i}{\\partial \\beta_{2}}, \\quad \\frac{\\partial \\ell_i }{\\partial \\beta_{3}},  \\quad \\frac{\\partial \\ell_i}{\\partial \\omega_{0}}, \\quad \\frac{\\partial \\ell_i}{\\partial \\omega_{1}}, \\quad \\frac{\\partial \\ell_i}{\\partial \\omega_{2}},  \\quad\\mbox{and} \\quad \\frac{\\partial \\ell_i}{\\partial \\omega_{3}}.\n",
+        "\\end{eqnarray*}"
+      ],
+      "metadata": {
+        "id": "1DmMo2w63CmT"
+      }
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "# import library\n",
+        "import numpy as np"
+      ],
+      "metadata": {
+        "id": "RIPaoVN834Lj"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "Let's first define the original function and the loss term:"
+      ],
+      "metadata": {
+        "id": "32-ufWhc3v2c"
+      }
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "AakK_qen3BpU"
+      },
+      "outputs": [],
+      "source": [
+        "# Defines the activation function\n",
+        "def paramReLU(gamma,x):\n",
+        "  if x > 0:\n",
+        "    return x\n",
+        "  else:\n",
+        "    return x * gamma\n",
+        "\n",
+        "# Defines the main function\n",
+        "def fn(x, beta0, beta1, beta2, beta3, omega0, omega1, omega2, omega3, gamma):\n",
+        "  return beta3+omega3 * paramReLU(gamma, beta2 + omega2 * paramReLU(gamma, beta1 + omega1 * paramReLU(gamma, beta0 + omega0 * x)))\n",
+        "\n",
+        "# Logistic sigmoid\n",
+        "def sig(z):\n",
+        "  return 1./(1+np.exp(-z))\n",
+        "\n",
+        "# The loss function (equation 5.20 from book)\n",
+        "def loss(f,y):\n",
+        "  sig_net_out = sig(f)\n",
+        "  l = -(1-y) * np.log(1-sig_net_out) - y * np.log(sig_net_out)\n",
+        "  return l"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "Now we'll choose some values for the betas and the omegas and x and compute the output of the function:"
+      ],
+      "metadata": {
+        "id": "y7tf0ZMt5OXt"
+      }
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "beta0 = 1.0; beta1 = -2.0; beta2 = -3.0; beta3 = 0.4\n",
+        "omega0 = 0.1; omega1 = -0.4; omega2 = 2.0; omega3 = -3.0\n",
+        "gamma = 0.2\n",
+        "x = 2.3; y =1.0\n",
+        "f_val = fn(x,beta0,beta1,beta2,beta3,omega0,omega1,omega2,omega3, gamma)\n",
+        "l_i_func = loss(f_val, y)\n",
+        "print('Loss full function = %3.3f'%l_i_func)"
+      ],
+      "metadata": {
+        "id": "pwvOcCxr41X_"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "# Forward pass\n",
+        "\n",
+        "We compute a series of intermediate values $f_0, h_0, f_1, h_1, f_2, h_2, f_3$, and finally the loss $\\ell$"
+      ],
+      "metadata": {
+        "id": "W6ZP62T5fU64"
+      }
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "x = 2.3; y =1.0\n",
+        "gamma = 0.2\n",
+        "# Compute all the f_k and h_k terms\n",
+        "# I've done the first two for you\n",
+        "f0 = beta0+omega0 * x\n",
+        "h1 = paramReLU(gamma, f0)\n",
+        "\n",
+        "\n",
+        "# TODO:  Replace the code below\n",
+        "f1 = 0\n",
+        "h2 = 0\n",
+        "f2 = 0\n",
+        "h3 = 0\n",
+        "f3 = 0\n",
+        "\n",
+        "\n",
+        "# Compute the loss and print\n",
+        "# The answer should be the same as when we computed the full function above\n",
+        "l_i = loss(f3, y)\n",
+        "print(\"Loss forward pass = %3.3f\"%(l_i))\n"
+      ],
+      "metadata": {
+        "id": "z-BckTpMf5PL"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "# Backward pass:  Derivative of loss function with respect to function output\n",
+        "\n",
+        "Now, we'll compute the derivative $\\frac{dl}{df_3}$ of the loss function with respect to the network output $f_3$.  In other words, we are asking how does the loss change as we make a small change in the network output.\n",
+        "\n",
+        "Since the loss it itself a function of $\\mbox{sig}[f_3]$ we'll compute this using the chain rule:\n",
+        "\n",
+        "\\begin{equation}\n",
+        "\\frac{dl}{df_3} = \\frac{d\\mbox{sig}[f_3]}{df_3}\\cdot \\frac{dl}{d\\mbox{sig}[f_3]}\n",
+        "\\end{equation}\n",
+        "\n",
+        "Your job is to compute the two quantities on the right hand side.\n"
+      ],
+      "metadata": {
+        "id": "TbFbxz64Xz4I"
+      }
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "# Compute the derivative of the the loss with respect to the function output f_val\n",
+        "def dl_df(f_val,y):\n",
+        "  # Compute sigmoid of network output\n",
+        "  sig_f_val = sig(f_val)\n",
+        "  # Compute the derivative of loss with respect to network output using chain rule\n",
+        "  dl_df_val = dsig_df(f_val) * dl_dsigf(sig_f_val, y)\n",
+        "  # Return the derivative\n",
+        "  return dl_df_val"
+      ],
+      "metadata": {
+        "id": "ZWKAq6HC90qV"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "# MOODLE ANSWER # Notebook V 1a: Copy this code when you have finished it.\n",
+        "\n",
+        "# Compute the derivative of the logistic sigmoid function with respect to its input (as a closed form solution)\n",
+        "def dsig_df(f_val):\n",
+        "  # TODO Write this function\n",
+        "  # Replace this line:\n",
+        "  return 1\n",
+        "\n",
+        "# Compute the derivative of the loss with respect to the logistic sigmoid (as a closed form solution)\n",
+        "def dl_dsigf(sig_f_val, y):\n",
+        "  # TODO Write this function\n",
+        "  # Replace this line:\n",
+        "  return 1"
+      ],
+      "metadata": {
+        "id": "lIngYAgPq-5I"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "Let's run that for some f_val, y.  Check previous practicals to see how you can check whether your answer is correct."
+      ],
+      "metadata": {
+        "id": "Q-j-i8khXzbK"
+      }
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "y = 0.0\n",
+        "dl_df3 = dl_df(f3,y)\n",
+        "print(\"Moodle Answer Notebook V 1b: dldh3=%3.3f\"%(dl_df3))\n",
+        "\n",
+        "y= 1.0\n",
+        "dl_df3 = dl_df(f3,y)\n",
+        "print(\"Moodle Answer Notebook V 1c: dldh3=%3.3f\"%(dl_df3))"
+      ],
+      "metadata": {
+        "id": "Z7Lb5BibY50H"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "# Backward pass:  Derivative of activation function with respect to preactivations\n",
+        "\n",
+        "Write a function to compute the derivative $\\frac{\\partial h}{\\partial f}$ of the activation function (parametric ReLU) with respect to its input.\n"
+      ],
+      "metadata": {
+        "id": "BA7QaOzejzZw"
+      }
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "# MOODLE ANSWER Notebook V 2a: Copy this code when you have finished it.\n",
+        "\n",
+        "def dh_df(gamma, f_val):\n",
+        "  # TODO:  Write this function\n",
+        "  # Replace this line:\n",
+        "  return 1\n"
+      ],
+      "metadata": {
+        "id": "bBPfPg04j-Qw"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "Let's run that for some values of f_val.  Check previous practicals to see how you can check whether your answer is correct."
+      ],
+      "metadata": {
+        "id": "QRNCM0EGk9-w"
+      }
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "f_val_test = 0.6\n",
+        "dh_df_val = dh_df(gamma, f_val_test)\n",
+        "print(\"Moodle Answer Notebook V 2b: dhdf=%3.3f\"%(dh_df_val))\n",
+        "\n",
+        "f_val_test = -0.4\n",
+        "dh_df_val = dh_df(gamma, f_val_test)\n",
+        "print(\"Moodle Answer Notebook V 2c: dhdf=%3.3f\"%(dh_df_val))"
+      ],
+      "metadata": {
+        "id": "bql8VZIGk8Wy"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        " # Backward pass:  Compute the derivatives of $l_i$ with respect to the intermediate quantities but in reverse order:\n",
+        "\n",
+        "\\begin{eqnarray}\n",
+        "\\frac{\\partial \\ell_i}{\\partial h_3}, \\quad \\frac{\\partial \\ell_i}{\\partial f_2}, \\quad\n",
+        "\\frac{\\partial \\ell_i}{\\partial h_2}, \\quad \\frac{\\partial \\ell_i}{\\partial f_1}, \\quad\\frac{\\partial \\ell_i}{\\partial h_1},  \\quad\\mbox{and} \\quad \\frac{\\partial \\ell_i}{\\partial f_0}.\n",
+        "\\end{eqnarray}\n",
+        "\n",
+        "The first of these derivatives can be calculated using the chain rule:\n",
+        "\n",
+        "\\begin{equation}\n",
+        "\\frac{\\partial \\ell_i}{\\partial h_{3}} =\\frac{\\partial f_{3}}{\\partial h_{3}} \\frac{\\partial \\ell_i}{\\partial f_{3}} .\n",
+        "\\end{equation}\n",
+        "\n",
+        "The left-hand side asks how $\\ell_i$ changes when $h_{3}$ changes.  The right-hand side says we can decompose this into (i) how $\\ell_i$ changes when $f_{3}$ changes and how $f_{3}$ changes when $h_{3}$ changes.  So you get a chain of events happening:  $h_{3}$ changes $f_{3}$, which changes $\\ell_i$, and the derivatives represent the effects of this chain.  Notice that we computed the first of these derivatives already.  The second term is the derivative of $\\beta_{3} + \\omega_{3}h_{3}$ with respect to $h_3$ which is simply $\\omega_3$.  \n",
+        "\n",
+        "We can continue in this way, computing the derivatives of the output with respect to these intermediate quantities:\n",
+        "\n",
+        "\\begin{eqnarray}\n",
+        "\\frac{\\partial \\ell_i}{\\partial f_{2}} &=& \\frac{\\partial h_{3}}{\\partial f_{2}}\\left(\n",
+        "\\frac{\\partial f_{3}}{\\partial h_{3}}\\frac{\\partial \\ell_i}{\\partial f_{3}} \\right)\n",
+        "\\nonumber \\\\\n",
+        "\\frac{\\partial \\ell_i}{\\partial h_{2}} &=& \\frac{\\partial f_{2}}{\\partial h_{2}}\\left(\\frac{\\partial h_{3}}{\\partial f_{2}}\\frac{\\partial f_{3}}{\\partial h_{3}}\\frac{\\partial \\ell_i}{\\partial f_{3}}\\right)\\nonumber \\\\\n",
+        "\\frac{\\partial \\ell_i}{\\partial f_{1}} &=& \\frac{\\partial h_{2}}{\\partial f_{1}}\\left( \\frac{\\partial f_{2}}{\\partial h_{2}}\\frac{\\partial h_{3}}{\\partial f_{2}}\\frac{\\partial f_{3}}{\\partial h_{3}}\\frac{\\partial \\ell_i}{\\partial f_{3}} \\right)\\nonumber \\\\\n",
+        "\\frac{\\partial \\ell_i}{\\partial h_{1}} &=& \\frac{\\partial f_{1}}{\\partial h_{1}}\\left(\\frac{\\partial h_{2}}{\\partial f_{1}} \\frac{\\partial f_{2}}{\\partial h_{2}}\\frac{\\partial h_{3}}{\\partial f_{2}}\\frac{\\partial f_{3}}{\\partial h_{3}}\\frac{\\partial \\ell_i}{\\partial f_{3}} \\right)\\nonumber \\\\\n",
+        "\\frac{\\partial \\ell_i}{\\partial f_{0}} &=& \\frac{\\partial h_{1}}{\\partial f_{0}}\\left(\\frac{\\partial f_{1}}{\\partial h_{1}}\\frac{\\partial h_{2}}{\\partial f_{1}} \\frac{\\partial f_{2}}{\\partial h_{2}}\\frac{\\partial h_{3}}{\\partial f_{2}}\\frac{\\partial f_{3}}{\\partial h_{3}}\\frac{\\partial \\ell_i}{\\partial f_{3}} \\right).\n",
+        "\\end{eqnarray}\n",
+        "\n",
+        "In each case, we have already computed all of the terms except the last one in the previous step, and the last term is simple to evaluate.  This is called the **backward pass**."
+      ],
+      "metadata": {
+        "id": "jay8NYWdFHuZ"
+      }
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "x = 2.3; y =1.0\n",
+        "dldf3 = dl_df(f3,y)"
+      ],
+      "metadata": {
+        "id": "RSC_2CIfKF1b"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "# MOODLE ANSWER Notebook V 3a: Copy this code when you have finished it.\n",
+        "# TODO -- Compute the derivatives of the output with respect\n",
+        "# to the intermediate computations h_k and f_k (i.e, run the backward pass)\n",
+        "# I've done the first two for you.  You replace the code below:\n",
+        "# Replace the code below\n",
+        "dldh3 = 1\n",
+        "dldf2 = 1\n",
+        "dldh2 = 1\n",
+        "dldf1 = 1\n",
+        "dldh1 = 1\n",
+        "dldf0 = 1"
+      ],
+      "metadata": {
+        "id": "gCQJeI--Egdl"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "Finally, we consider how the loss~$\\ell_{i}$ changes when we change the parameters $\\beta_{\\bullet}$ and $\\omega_{\\bullet}$. Once more, we apply the chain rule:\n",
+        "\n",
+        "\n",
+        "\n",
+        "\n",
+        "\\begin{eqnarray}\n",
+        "\\frac{\\partial \\ell_i}{\\partial \\beta_{k}} &=& \\frac{\\partial f_{k}}{\\partial \\beta_{k}}\\frac{\\partial \\ell_i}{\\partial f_{k}}\\nonumber \\\\\n",
+        "\\frac{\\partial \\ell_i}{\\partial \\omega_{k}} &=& \\frac{\\partial f_{k}}{\\partial \\omega_{k}}\\frac{\\partial \\ell_i}{\\partial f_{k}}.\n",
+        "\\end{eqnarray}\n",
+        "\n",
+        "\\noindent In each case, the second term on the right-hand side was computed in step 2. When $k>0$, we have~$f_{k}=\\beta_{k}+\\omega_k \\cdot h_{k}$, so:\n",
+        "\n",
+        "\\begin{eqnarray}\n",
+        "\\frac{\\partial f_{k}}{\\partial \\beta_{k}} = 1 \\quad\\quad\\mbox{and}\\quad \\quad \\frac{\\partial f_{k}}{\\partial \\omega_{k}} &=& h_{k}.\n",
+        "\\end{eqnarray}"
+      ],
+      "metadata": {
+        "id": "FlzlThQPGpkU"
+      }
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "# MOODLE ANSWER Notebook V 3b: Copy this code when you have finished it.\n",
+        "# TODO -- Calculate the final derivatives with respect to the beta and omega terms\n",
+        "# Replace these terms\n",
+        "dldbeta3 = 1\n",
+        "dldomega3 = 1\n",
+        "dldbeta2 = 1\n",
+        "dldomega2 = 1\n",
+        "dldbeta1 = 1\n",
+        "dldomega1 = 1\n",
+        "dldbeta0 = 1\n",
+        "dldomega0 = 1"
+      ],
+      "metadata": {
+        "id": "1I2BhqZhGMK6"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "# Print the last two values out (enter these into Moodle).  Again, think about how you can test whether these are correct.\n",
+        "print('Moodle Answer Notebook V 3c: dldbeta0=%3.3f'%(dldbeta0))\n",
+        "print('Moodle Answer Notebook V 3d: dldOmega0=%3.3f'%(dldomega0))"
+      ],
+      "metadata": {
+        "id": "38eiOn2aHgHI"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "# Compute the derivatives of  $\\ell_i$  with respect to the parmeter $\\gamma$ of the parametric ReLU function.  \n",
+        "\n",
+        "In other words, compute:\n",
+        "\n",
+        "\\begin{equation}\n",
+        "\\frac{d\\ell_i}{d\\gamma}\n",
+        "\\end{equation}\n",
+        "\n",
+        "Along the way, we will need to compute derivatives\n",
+        "\n",
+        "\\begin{equation}\n",
+        "\\frac{dh_k(\\gamma,f_{k-1})}{d\\gamma}\n",
+        "\\end{equation}\n",
+        "\n",
+        "This is quite difficult and not worth many marks, so don't spend too much time on it if you are confused!"
+      ],
+      "metadata": {
+        "id": "lhD5AoUHx3DS"
+      }
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "# Computes how an activation changes with a small change in gamma assuming preactivations are f\n",
+        "# MOODLE ANSWER # Notebook V 4a: Copy this code when you have finished it.\n",
+        "def dhdgamma(gamma, f):\n",
+        "  # TODO -- Write this function\n",
+        "  # Replace this line\n",
+        "  return 1"
+      ],
+      "metadata": {
+        "id": "yC-9MTQevliP"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "# Compute how the loss changes with gamma\n",
+        "# Replace this line:\n",
+        "# MOODLE ANSWER # Notebook V 4b: Copy this code when you have finished it.\n",
+        "dldgamma = 1"
+      ],
+      "metadata": {
+        "id": "DiNQrveoLuHR"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "print(\"Moodle Answer Notebook V 4c: dldgamma = %3.3f\"%(dldgamma))"
+      ],
+      "metadata": {
+        "id": "YHxmAEnxzy3O"
+      },
+      "execution_count": null,
+      "outputs": []
+    }
+  ]
+}

Notebooks/Chap01/1_1_BackgroundMathematics.ipynb

@@ -1,16 +1,18 @@
 {
   "cells": [
     {
+      "attachments": {},
       "cell_type": "markdown",
       "metadata": {
-        "id": "view-in-github",
+        "colab_type": "text",
-        "colab_type": "text"
+        "id": "view-in-github"
       },
       "source": [
         "<a href=\"https://colab.research.google.com/github/udlbook/udlbook/blob/main/Notebooks/Chap01/1_1_BackgroundMathematics.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
       ]
     },
     {
+      "attachments": {},
       "cell_type": "markdown",
       "metadata": {
         "id": "s5zzKSOusPOB"
@@ -39,6 +41,7 @@
       ]
     },
     {
+      "attachments": {},
       "cell_type": "markdown",
       "metadata": {
         "id": "WV2Dl6owme2d"
@@ -46,11 +49,11 @@
       "source": [
         "**Linear functions**<br> We will be using the term *linear equation* to mean a weighted sum of inputs plus an offset. If there is just one input $x$, then this is a straight line:\n",
         "\n",
-        "\\begin{equation}y=\\beta+\\omega x,\\end{equation} <br>\n",
+        "\\begin{equation}y=\\beta+\\omega x,\\end{equation} \n",
         "\n",
         "where $\\beta$ is the y-intercept of the linear and $\\omega$ is the slope of the line. When there are two inputs $x_{1}$ and $x_{2}$, then this becomes:\n",
         "\n",
-        "\\begin{equation}y=\\beta+\\omega_1 x_1 + \\omega_2 x_2.\\end{equation} <br><br>\n",
+        "\\begin{equation}y=\\beta+\\omega_1 x_1 + \\omega_2 x_2.\\end{equation} \n",
         "\n",
         "Any other functions are by definition **non-linear**.\n",
         "\n",
@@ -83,7 +86,7 @@
       "source": [
         "# Plot the 1D linear function\n",
         "\n",
-        "# Define an array of x values from 0 to 10 with increments of 0.1\n",
+        "# Define an array of x values from 0 to 10 with increments of 0.01\n",
         "# https://numpy.org/doc/stable/reference/generated/numpy.arange.html\n",
         "x = np.arange(0.0,10.0, 0.01)\n",
         "# Compute y using the function you filled in above\n",
@@ -104,6 +107,7 @@
       ]
     },
     {
+      "attachments": {},
       "cell_type": "markdown",
       "metadata": {
         "id": "AedfvD9dxShZ"
@@ -171,7 +175,7 @@
         "# Color represents y value (brighter = higher value)\n",
         "# Black = -10 or less, White = +10 or more\n",
         "# 0 = mid orange\n",
-        "# Lines are conoturs where value is equal\n",
+        "# Lines are contours where value is equal\n",
         "draw_2D_function(x1,x2,y)\n",
         "\n",
         "# TODO\n",
@@ -188,6 +192,7 @@
       ]
     },
     {
+      "attachments": {},
       "cell_type": "markdown",
       "metadata": {
         "id": "i8tLwpls476R"
@@ -195,15 +200,15 @@
       "source": [
         "Often we will want to compute many linear functions at the same time.  For example, we might have three inputs, $x_1$, $x_2$, and $x_3$ and want to compute two linear functions giving $y_1$ and $y_2$. Of course, we could do this by just running each equation separately,<br><br>\n",
         "\n",
-        "\\begin{eqnarray}y_1 &=& \\beta_1 + \\omega_{11} x_1 + \\omega_{12} x_2 + \\omega_{13} x_3\\\\\n",
+        "\\begin{align}y_1 &=& \\beta_1 + \\omega_{11} x_1 + \\omega_{12} x_2 + \\omega_{13} x_3\\\\\n",
         "y_2 &=& \\beta_2 + \\omega_{21} x_1 + \\omega_{22} x_2 + \\omega_{23} x_3.\n",
-        "\\end{eqnarray}<br>\n",
+        "\\end{align}\n",
         "\n",
         "However, we can write it more compactly with vectors and matrices:\n",
         "\n",
         "\\begin{equation}\n",
         "\\begin{bmatrix} y_1\\\\ y_2 \\end{bmatrix} = \\begin{bmatrix}\\beta_{1}\\\\\\beta_{2}\\end{bmatrix}+ \\begin{bmatrix}\\omega_{11}&\\omega_{12}&\\omega_{13}\\\\\\omega_{21}&\\omega_{22}&\\omega_{23}\\end{bmatrix}\\begin{bmatrix}x_{1}\\\\x_{2}\\\\x_{3}\\end{bmatrix},\n",
-        "\\end{equation}<br>\n",
+        "\\end{equation}\n",
         "or\n",
         "\n",
         "\\begin{equation}\n",
@@ -231,6 +236,7 @@
       ]
     },
     {
+      "attachments": {},
       "cell_type": "markdown",
       "metadata": {
         "id": "fGzVJQ6N-mHJ"
@@ -273,6 +279,7 @@
       ]
     },
     {
+      "attachments": {},
       "cell_type": "markdown",
       "metadata": {
         "id": "3LGRoTMLU8ZU"
@@ -286,6 +293,7 @@
       ]
     },
     {
+      "attachments": {},
       "cell_type": "markdown",
       "metadata": {
         "id": "7Y5zdKtKZAB2"
@@ -295,7 +303,7 @@
         "\n",
         "Throughout the book, we'll be using some special functions (see Appendix B.1.3).  The most important of these are the logarithm and exponential functions.  Let's investigate their properties.\n",
         "\n",
-        "We'll start with the exponential function $y=\\mbox{exp}[x]=e^x$ which maps the real line $[-\\infty,+\\infty]$ to non-negative numbers $[0,+\\infty]$."
+        "We'll start with the exponential function $y=\\exp[x]=e^x$ which maps the real line $[-\\infty,+\\infty]$ to non-negative numbers $[0,+\\infty]$."
       ]
     },
     {
@@ -308,7 +316,7 @@
       "source": [
         "# Draw the exponential function\n",
         "\n",
-        "# Define an array of x values from -5 to 5 with increments of 0.1\n",
+        "# Define an array of x values from -5 to 5 with increments of 0.01\n",
         "x = np.arange(-5.0,5.0, 0.01)\n",
         "y = np.exp(x) ;\n",
         "\n",
@@ -321,6 +329,7 @@
       ]
     },
     {
+      "attachments": {},
       "cell_type": "markdown",
       "metadata": {
         "id": "XyrT8257IWCu"
@@ -328,14 +337,15 @@
       "source": [
         "# Questions\n",
         "\n",
-        "1. What is $\\mbox{exp}[0]$?  \n",
+        "1. What is $\\exp[0]$?  \n",
-        "2. What is $\\mbox{exp}[1]$?\n",
+        "2. What is $\\exp[1]$?\n",
-        "3. What is $\\mbox{exp}[-\\infty]$?\n",
+        "3. What is $\\exp[-\\infty]$?\n",
-        "4. What is $\\mbox{exp}[+\\infty]$?\n",
+        "4. What is $\\exp[+\\infty]$?\n",
         "5. A function is convex if we can draw a straight line between any two points on the function, and this line always lies above the function. Similarly, a function is concave if a straight line between any two points always lies below the function.  Is the exponential function convex or concave or neither?\n"
       ]
     },
     {
+      "attachments": {},
       "cell_type": "markdown",
       "metadata": {
         "id": "R6A4e5IxIWCu"
@@ -354,7 +364,7 @@
       "source": [
         "# Draw the logarithm function\n",
         "\n",
-        "# Define an array of x values from -5 to 5 with increments of 0.1\n",
+        "# Define an array of x values from -5 to 5 with increments of 0.01\n",
         "x = np.arange(0.01,5.0, 0.01)\n",
         "y = np.log(x) ;\n",
         "\n",
@@ -367,6 +377,7 @@
       ]
     },
     {
+      "attachments": {},
       "cell_type": "markdown",
       "metadata": {
         "id": "yYWrL5AXIWCv"
@@ -374,20 +385,20 @@
       "source": [
         "# Questions\n",
         "\n",
-        "1. What is $\\mbox{log}[0]$?  \n",
+        "1. What is $\\log[0]$?  \n",
-        "2. What is $\\mbox{log}[1]$?\n",
+        "2. What is $\\log[1]$?\n",
-        "3. What is $\\mbox{log}[e]$?\n",
+        "3. What is $\\log[e]$?\n",
-        "4. What is $\\mbox{log}[\\exp[3]]$?\n",
+        "4. What is $\\log[\\exp[3]]$?\n",
-        "5. What is $\\mbox{exp}[\\log[4]]$?\n",
+        "5. What is $\\exp[\\log[4]]$?\n",
-        "6. What is $\\mbox{log}[-1]$?\n",
+        "6. What is $\\log[-1]$?\n",
         "7. Is the logarithm function concave or convex?\n"
       ]
     }
   ],
   "metadata": {
     "colab": {
-      "provenance": [],
+      "include_colab_link": true,
-      "include_colab_link": true
+      "provenance": []
     },
     "kernelspec": {
       "display_name": "Python 3 (ipykernel)",

Notebooks/Chap02/2_1_Supervised_Learning.ipynb

@@ -31,7 +31,7 @@
       "source": [
         "# Notebook 2.1 Supervised Learning\n",
         "\n",
-        "The purpose of this notebook is to explore the linear regression model dicussed in Chapter 2 of the book.\n",
+        "The purpose of this notebook is to explore the linear regression model discussed in Chapter 2 of the book.\n",
         "\n",
         "Work through the cells below, running each cell in turn. In various places you will see the words \"TO DO\". Follow the instructions at these places and write code to complete the functions. There are also questions interspersed in the text.\n",
         "\n",
@@ -213,7 +213,7 @@
         "\n",
         "# Make a 2D array for the losses\n",
         "all_losses = np.zeros_like(phi1_mesh)\n",
-        "# Run throught each 2D combination of phi0, phi1 and compute loss\n",
+        "# Run through each 2D combination of phi0, phi1 and compute loss\n",
         "for indices,temp in np.ndenumerate(phi1_mesh):\n",
         "    all_losses[indices] = compute_loss(x,y, phi0_mesh[indices], phi1_mesh[indices])\n"
       ],
@@ -250,4 +250,4 @@
       "outputs": []
     }
   ]
-}
+}

Notebooks/Chap03/3_2_Shallow_Networks_II.ipynb

@@ -4,7 +4,6 @@
   "metadata": {
     "colab": {
       "provenance": [],
-      "authorship_tag": "ABX9TyNk2dAhwwRxGpfVSC3b2Owv",
       "include_colab_link": true
     },
     "kernelspec": {
@@ -182,7 +181,7 @@
     {
       "cell_type": "markdown",
       "source": [
-        "Now we'll extend this model to have two outputs $y_1$ and $y_2$, each of which can be visualized with a separate heatmap.  You will now have sets of parameters $\\phi_{10}, \\phi_{11},\\phi_{12}$ and $\\phi_{20}, \\phi_{21},\\phi_{22}$ that correspond to each of these outputs."
+        "Now we'll extend this model to have two outputs $y_1$ and $y_2$, each of which can be visualized with a separate heatmap.  You will now have sets of parameters $\\phi_{10}, \\phi_{11}, \\phi_{12}, \\phi_{13}$ and $\\phi_{20}, \\phi_{21}, \\phi_{22}, \\phi_{23}$ that correspond to each of these outputs."
       ],
       "metadata": {
         "id": "Xl6LcrUyM7Lh"

Notebooks/Chap03/3_3_Shallow_Network_Regions.ipynb

@@ -48,7 +48,7 @@
         "import numpy as np\n",
         "# Imports plotting library\n",
         "import matplotlib.pyplot as plt\n",
-        "# Imports math libray\n",
+        "# Imports math library\n",
         "import math"
       ],
       "metadata": {
@@ -79,7 +79,7 @@
       "source": [
         "def number_regions(Di, D):\n",
         "  # TODO -- implement Zaslavsky's formula\n",
-        "  # You can use math.com() https://www.w3schools.com/python/ref_math_comb.asp\n",
+        "  # You can use math.comb() https://www.w3schools.com/python/ref_math_comb.asp\n",
         "  # Replace this code\n",
         "  N = 1;\n",
         "\n",
@@ -102,7 +102,7 @@
     {
       "cell_type": "code",
       "source": [
-        "# Calculate the number of regions for 10D input (Di=2) and 50 hidden units (D=50)\n",
+        "# Calculate the number of regions for 10D input (Di=10) and 50 hidden units (D=50)\n",
         "N = number_regions(10, 50)\n",
         "print(f\"Di=10, D=50, Number of regions = {int(N)}, True value = 13432735556\")"
       ],
@@ -126,7 +126,7 @@
     {
       "cell_type": "code",
       "source": [
-        "# Show that calculation fails when $D_i < D$\n",
+        "# Depending on how you implemented it, the calculation may fail when $D_i > D$ (not to worry...)\n",
         "try:\n",
         "  N = number_regions(10, 8)\n",
         "  print(f\"Di=10, D=8, Number of regions = {int(N)}, True value = 256\")\n",
@@ -256,4 +256,4 @@
       "outputs": []
     }
   ]
-}
+}

Notebooks/Chap03/3_4_Activation_Functions.ipynb

@@ -1,33 +1,22 @@
 {
-  "nbformat": 4,
-  "nbformat_minor": 0,
-  "metadata": {
-    "colab": {
-      "provenance": [],
-      "authorship_tag": "ABX9TyPmra+JD+dm2M3gCqx3bMak",
-      "include_colab_link": true
-    },
-    "kernelspec": {
-      "name": "python3",
-      "display_name": "Python 3"
-    },
-    "language_info": {
-      "name": "python"
-    }
-  },
   "cells": [
     {
+      "attachments": {},
       "cell_type": "markdown",
       "metadata": {
-        "id": "view-in-github",
+        "colab_type": "text",
-        "colab_type": "text"
+        "id": "view-in-github"
       },
       "source": [
         "<a href=\"https://colab.research.google.com/github/udlbook/udlbook/blob/main/Notebooks/Chap03/3_4_Activation_Functions.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
       ]
     },
     {
+      "attachments": {},
       "cell_type": "markdown",
+      "metadata": {
+        "id": "Mn0F56yY8ohX"
+      },
       "source": [
         "# **Notebook 3.4 -- Activation functions**\n",
         "\n",
@@ -36,10 +25,7 @@
         "Work through the cells below, running each cell in turn. In various places you will see the words \"TO DO\". Follow the instructions at these places and write code to complete the functions. There are also questions interspersed in the text.\n",
         "\n",
         "Contact me at udlbookmail@gmail.com if you find any mistakes or have any suggestions."
-      ],
+      ]
-      "metadata": {
-        "id": "Mn0F56yY8ohX"
-      }
     },
     {
       "cell_type": "code",
@@ -57,6 +43,11 @@
     },
     {
       "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "AeHzflFt9Tgn"
+      },
+      "outputs": [],
       "source": [
         "# Plot the shallow neural network.  We'll assume input in is range [0,1] and output [-1,1]\n",
         "# If the plot_all flag is set to true, then we'll plot all the intermediate stages as in Figure 3.3\n",
@@ -94,15 +85,15 @@
         "    for i in range(len(x_data)):\n",
         "      ax.plot(x_data[i], y_data[i],)\n",
         "  plt.show()"
-      ],
+      ]
-      "metadata": {
-        "id": "AeHzflFt9Tgn"
-      },
-      "execution_count": null,
-      "outputs": []
     },
     {
       "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "7qeIUrh19AkH"
+      },
+      "outputs": [],
       "source": [
         "# Define a shallow neural network with, one input, one output, and three hidden units\n",
         "def shallow_1_1_3(x, activation_fn, phi_0,phi_1,phi_2,phi_3, theta_10, theta_11, theta_20, theta_21, theta_30, theta_31):\n",
@@ -123,38 +114,39 @@
         "\n",
         "  # Return everything we have calculated\n",
         "  return y, pre_1, pre_2, pre_3, act_1, act_2, act_3, w_act_1, w_act_2, w_act_3"
-      ],
+      ]
-      "metadata": {
-        "id": "7qeIUrh19AkH"
-      },
-      "execution_count": null,
-      "outputs": []
     },
     {
       "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "cwTp__Fk9YUx"
+      },
+      "outputs": [],
       "source": [
         "# Define the Rectified Linear Unit (ReLU) function\n",
         "def ReLU(preactivation):\n",
         "  activation = preactivation.clip(0.0)\n",
         "  return activation"
-      ],
+      ]
-      "metadata": {
-        "id": "cwTp__Fk9YUx"
-      },
-      "execution_count": null,
-      "outputs": []
     },
     {
+      "attachments": {},
       "cell_type": "markdown",
-      "source": [
-        "First, let's run the network with a ReLU functions"
-      ],
       "metadata": {
         "id": "INQkRzyn9kVC"
-      }
+      },
+      "source": [
+        "First, let's run the network with a ReLU functions"
+      ]
     },
     {
       "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "jT9QuKou9i0_"
+      },
+      "outputs": [],
       "source": [
         "# Now lets define some parameters and run the neural network\n",
         "theta_10 =  0.3 ; theta_11 = -1.0\n",
@@ -170,15 +162,14 @@
         "    shallow_1_1_3(x, ReLU, phi_0,phi_1,phi_2,phi_3, theta_10, theta_11, theta_20, theta_21, theta_30, theta_31)\n",
         "# And then plot it\n",
         "plot_neural(x, y, pre_1, pre_2, pre_3, act_1, act_2, act_3, w_act_1, w_act_2, w_act_3, plot_all=True)"
-      ],
+      ]
-      "metadata": {
-        "id": "jT9QuKou9i0_"
-      },
-      "execution_count": null,
-      "outputs": []
     },
     {
+      "attachments": {},
       "cell_type": "markdown",
+      "metadata": {
+        "id": "-I8N7r1o9HYf"
+      },
       "source": [
         "# Sigmoid activation function\n",
         "\n",
@@ -189,13 +180,15 @@
         "\\end{equation}\n",
         "\n",
         "(Note that the factor of 10 is not standard -- but it allow us to plot on the same axes as the ReLU examples)"
-      ],
+      ]
-      "metadata": {
-        "id": "-I8N7r1o9HYf"
-      }
     },
     {
       "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "hgkioNyr975Y"
+      },
+      "outputs": [],
       "source": [
         "# Define the sigmoid function\n",
         "def sigmoid(preactivation):\n",
@@ -204,15 +197,15 @@
         "  activation = np.zeros_like(preactivation);\n",
         "\n",
         "  return activation"
-      ],
+      ]
-      "metadata": {
-        "id": "hgkioNyr975Y"
-      },
-      "execution_count": null,
-      "outputs": []
     },
     {
       "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "94HIXKJH97ve"
+      },
+      "outputs": [],
       "source": [
         "# Make an array of inputs\n",
         "z = np.arange(-1,1,0.01)\n",
@@ -223,25 +216,26 @@
         "ax.plot(z,sig_z,'r-')\n",
         "ax.set_xlim([-1,1]);ax.set_ylim([0,1])\n",
         "ax.set_xlabel('z'); ax.set_ylabel('sig[z]')\n",
-        "plt.show"
+        "plt.show()"
-      ],
+      ]
-      "metadata": {
-        "id": "94HIXKJH97ve"
-      },
-      "execution_count": null,
-      "outputs": []
     },
     {
+      "attachments": {},
       "cell_type": "markdown",
-      "source": [
-        "Let's see what happens when we use this activation function in a neural network"
-      ],
       "metadata": {
         "id": "p3zQNXhj-J-o"
-      }
+      },
+      "source": [
+        "Let's see what happens when we use this activation function in a neural network"
+      ]
     },
     {
       "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "C1dASr9L-GNt"
+      },
+      "outputs": [],
       "source": [
         "theta_10 =  0.3 ; theta_11 = -1.0\n",
         "theta_20 = -1.0  ; theta_21 = 2.0\n",
@@ -256,39 +250,41 @@
         "    shallow_1_1_3(x, sigmoid, phi_0,phi_1,phi_2,phi_3, theta_10, theta_11, theta_20, theta_21, theta_30, theta_31)\n",
         "# And then plot it\n",
         "plot_neural(x, y, pre_1, pre_2, pre_3, act_1, act_2, act_3, w_act_1, w_act_2, w_act_3, plot_all=True)"
-      ],
+      ]
-      "metadata": {
-        "id": "C1dASr9L-GNt"
-      },
-      "execution_count": null,
-      "outputs": []
     },
     {
+      "attachments": {},
       "cell_type": "markdown",
-      "source": [
-        "You probably notice that this gives nice smooth curves.  So why don't we use this?  Aha... it's not obvious right now, but we will get to it when we learn to fit models."
-      ],
       "metadata": {
         "id": "Uuam_DewA9fH"
-      }
+      },
+      "source": [
+        "You probably notice that this gives nice smooth curves.  So why don't we use this?  Aha... it's not obvious right now, but we will get to it when we learn to fit models."
+      ]
     },
     {
+      "attachments": {},
       "cell_type": "markdown",
+      "metadata": {
+        "id": "C9WKkcMUABze"
+      },
       "source": [
         "# Heaviside activation function\n",
         "\n",
         "The Heaviside function is defined as:\n",
         "\n",
         "\\begin{equation}\n",
-        "\\mbox{heaviside}[z] = \\begin{cases} 0 & \\quad z <0 \\\\ 1 & \\quad z\\geq 0\\end{cases}\n",
+        "\\text{heaviside}[z] = \\begin{cases} 0 & \\quad z <0 \\\\ 1 & \\quad z\\geq 0\\end{cases}\n",
         "\\end{equation}"
-      ],
+      ]
-      "metadata": {
-        "id": "C9WKkcMUABze"
-      }
     },
     {
       "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "-1qFkdOL-NPc"
+      },
+      "outputs": [],
       "source": [
         "# Define the heaviside function\n",
         "def heaviside(preactivation):\n",
@@ -299,15 +295,15 @@
         "\n",
         "\n",
         "  return activation"
-      ],
+      ]
-      "metadata": {
-        "id": "-1qFkdOL-NPc"
-      },
-      "execution_count": null,
-      "outputs": []
     },
     {
       "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "mSPyp7iA-44H"
+      },
+      "outputs": [],
       "source": [
         "# Make an array of inputs\n",
         "z = np.arange(-1,1,0.01)\n",
@@ -318,16 +314,16 @@
         "ax.plot(z,heav_z,'r-')\n",
         "ax.set_xlim([-1,1]);ax.set_ylim([-2,2])\n",
         "ax.set_xlabel('z'); ax.set_ylabel('heaviside[z]')\n",
-        "plt.show"
+        "plt.show()"
-      ],
+      ]
-      "metadata": {
-        "id": "mSPyp7iA-44H"
-      },
-      "execution_count": null,
-      "outputs": []
     },
     {
       "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "t99K2lSl--Mq"
+      },
+      "outputs": [],
       "source": [
         "theta_10 =  0.3 ; theta_11 = -1.0\n",
         "theta_20 = -1.0  ; theta_21 = 2.0\n",
@@ -342,39 +338,41 @@
         "    shallow_1_1_3(x, heaviside, phi_0,phi_1,phi_2,phi_3, theta_10, theta_11, theta_20, theta_21, theta_30, theta_31)\n",
         "# And then plot it\n",
         "plot_neural(x, y, pre_1, pre_2, pre_3, act_1, act_2, act_3, w_act_1, w_act_2, w_act_3, plot_all=True)"
-      ],
+      ]
-      "metadata": {
-        "id": "t99K2lSl--Mq"
-      },
-      "execution_count": null,
-      "outputs": []
     },
     {
+      "attachments": {},
       "cell_type": "markdown",
-      "source": [
-        "This can approximate any function, but the output is discontinuous, and there are also reasons not to use it that we will discover when we learn more about model fitting."
-      ],
       "metadata": {
         "id": "T65MRtM-BCQA"
-      }
+      },
+      "source": [
+        "This can approximate any function, but the output is discontinuous, and there are also reasons not to use it that we will discover when we learn more about model fitting."
+      ]
     },
     {
+      "attachments": {},
       "cell_type": "markdown",
+      "metadata": {
+        "id": "RkB-XZMLBTaR"
+      },
       "source": [
         "# Linear activation functions\n",
         "\n",
         "Neural networks don't work if the activation function is linear.  For example, consider what would happen if the activation function was:\n",
         "\n",
         "\\begin{equation}\n",
-        "\\mbox{lin}[z] = a + bz\n",
+        "\\text{lin}[z] = a + bz\n",
         "\\end{equation}"
-      ],
+      ]
-      "metadata": {
-        "id": "RkB-XZMLBTaR"
-      }
     },
     {
       "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "Q59v3saj_jq1"
+      },
+      "outputs": [],
       "source": [
         "# Define the linear activation function\n",
         "def lin(preactivation):\n",
@@ -384,15 +382,15 @@
         "  activation = a+b * preactivation\n",
         "  # Return\n",
         "  return activation"
-      ],
+      ]
-      "metadata": {
-        "id": "Q59v3saj_jq1"
-      },
-      "execution_count": null,
-      "outputs": []
     },
     {
       "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "IwodsBr0BkDn"
+      },
+      "outputs": [],
       "source": [
         "# TODO\n",
         "# 1. The linear activation function above just returns the input: (0+1*z) = z\n",
@@ -415,12 +413,23 @@
         "    shallow_1_1_3(x, lin, phi_0,phi_1,phi_2,phi_3, theta_10, theta_11, theta_20, theta_21, theta_30, theta_31)\n",
         "# And then plot it\n",
         "plot_neural(x, y, pre_1, pre_2, pre_3, act_1, act_2, act_3, w_act_1, w_act_2, w_act_3, plot_all=True)"
-      ],
+      ]
-      "metadata": {
-        "id": "IwodsBr0BkDn"
-      },
-      "execution_count": null,
-      "outputs": []
     }
-  ]
+  ],
-}
+  "metadata": {
+    "colab": {
+      "authorship_tag": "ABX9TyOmxhh3ymYWX+1HdZ91I6zU",
+      "include_colab_link": true,
+      "provenance": []
+    },
+    "kernelspec": {
+      "display_name": "Python 3",
+      "name": "python3"
+    },
+    "language_info": {
+      "name": "python"
+    }
+  },
+  "nbformat": 4,
+  "nbformat_minor": 0
+}

Notebooks/Chap04/4_1_Composing_Networks.ipynb

@@ -4,7 +4,6 @@
   "metadata": {
     "colab": {
       "provenance": [],
-      "authorship_tag": "ABX9TyPEQEGetZqWnLRNn99Q2aaT",
       "include_colab_link": true
     },
     "kernelspec": {
@@ -220,7 +219,7 @@
       "source": [
         "# TODO\n",
         "# Take a piece of paper and draw what you think will happen when we feed the\n",
-        "# output of the first network into the second one now that we have changed it.  Draw the relationship between\n",
+        "# output of the first network into the modified second network.  Draw the relationship between\n",
         "# the input of the first network and the output of the second one."
       ],
       "metadata": {
@@ -261,7 +260,7 @@
       "source": [
         "# TODO\n",
         "# Take a piece of paper and draw what you think will happen when we feed the\n",
-        "# output of the first network now we have changed it into the original second network.  Draw the relationship between\n",
+        "# output of the modified first network into the original second network.  Draw the relationship between\n",
         "# the input of the first network and the output of the second one."
       ],
       "metadata": {
@@ -302,7 +301,7 @@
       "source": [
         "# TODO\n",
         "# Take a piece of paper and draw what you think will happen when we feed the\n",
-        "# output of the first network into the original second network.  Draw the relationship between\n",
+        "# output of the first network into the a copy of itself.  Draw the relationship between\n",
         "# the input of the first network and the output of the second one."
       ],
       "metadata": {
@@ -350,7 +349,7 @@
         "# network (blue curve above)\n",
         "\n",
         "# Take away conclusion:  with very few parameters, we can make A LOT of linear regions, but\n",
-        "# they depend on one another in complex ways that quickly become to difficult to understand intuitively."
+        "# they depend on one another in complex ways that quickly become too difficult to understand intuitively."
       ],
       "metadata": {
         "id": "HqzePCLOVQK7"

Notebooks/Chap04/4_3_Deep_Networks.ipynb

@@ -4,7 +4,7 @@
   "metadata": {
     "colab": {
       "provenance": [],
-      "authorship_tag": "ABX9TyPyaqr0yJlxfIcTpfLSHDrP",
+      "authorship_tag": "ABX9TyO2DaD75p+LGi7WgvTzjrk1",
       "include_colab_link": true
     },
     "kernelspec": {
@@ -101,7 +101,6 @@
       "cell_type": "code",
       "source": [
         "# # Plot the shallow neural network.  We'll assume input in is range [-1,1] and output [-1,1]\n",
-        "# If the plot_all flag is set to true, then we'll plot all the intermediate stages as in Figure 3.3\n",
         "def plot_neural(x, y):\n",
         "  fig, ax = plt.subplots()\n",
         "  ax.plot(x.T,y.T)\n",
@@ -119,7 +118,7 @@
     {
       "cell_type": "markdown",
       "source": [
-        "Let's define a networks.  We'll just consider the inputs and outputs over the range [-1,1].  If you set the \"plot_all\" flat to True,  you can see the details of how it was created."
+        "Let's define a network.  We'll just consider the inputs and outputs over the range [-1,1].  If you set the \"plot_all\" flat to True,  you can see the details of how it was created."
       ],
       "metadata": {
         "id": "LxBJCObC-NTY"
@@ -232,7 +231,7 @@
         "beta_2 = np.zeros((1,1))\n",
         "Omega_2 = np.zeros((1,3))\n",
         "\n",
-        "# TODO Fill in the values of the beta and Omega matrices for with the n1_theta, n1_phi, n2_theta, and n2_phi parameters\n",
+        "# TODO Fill in the values of the beta and Omega matrices for the n1_theta, n1_phi, n2_theta, and n2_phi parameters\n",
         "# that define the composition of the two networks above (see eqn 4.5 for Omega1 and beta1 albeit in different notation)\n",
         "# !!! NOTE THAT MATRICES ARE CONVENTIONALLY INDEXED WITH a_11 IN THE TOP LEFT CORNER, BUT NDARRAYS START AT [0,0] SO EVERYTHING IS OFFSET\n",
         "# To get you started I've filled in a few:\n",
@@ -319,4 +318,4 @@
       "outputs": []
     }
   ]
-}
+}

Notebooks/Chap05/5_1_Least_Squares_Loss.ipynb

@@ -4,7 +4,6 @@
   "metadata": {
     "colab": {
       "provenance": [],
-      "authorship_tag": "ABX9TyPX88BLalmJTle9GSAZMJcz",
       "include_colab_link": true
     },
     "kernelspec": {
@@ -66,7 +65,7 @@
         "  return activation\n",
         "\n",
         "# Define a shallow neural network\n",
-        "def shallow_nn(x, beta_0, omega_0, beta_1, omaga_1):\n",
+        "def shallow_nn(x, beta_0, omega_0, beta_1, omega_1):\n",
         "    # Make sure that input data is (1 x n_data) array\n",
         "    n_data = x.size\n",
         "    x = np.reshape(x,(1,n_data))\n",
@@ -139,7 +138,7 @@
       "source": [
         "# Univariate regression\n",
         "\n",
-        "We'll investigate a simple univarite regression situation with a single input $x$ and a single output $y$ as pictured in figures 5.4 and 5.5b."
+        "We'll investigate a simple univariate regression situation with a single input $x$ and a single output $y$ as pictured in figures 5.4 and 5.5b."
       ],
       "metadata": {
         "id": "PsgLZwsPxauP"
@@ -186,7 +185,7 @@
     {
       "cell_type": "code",
       "source": [
-        "# Return probability under normal distribution for input x\n",
+        "# Return probability under normal distribution\n",
         "def normal_distribution(y, mu, sigma):\n",
         "    # TODO-- write in the equation for the normal distribution\n",
         "    # Equation 5.7 from the notes (you will need np.sqrt() and np.exp(), and math.pi)\n",
@@ -306,7 +305,8 @@
       "source": [
         "# Return the negative log likelihood of the data under the model\n",
         "def compute_negative_log_likelihood(y_train, mu, sigma):\n",
-        "  # TODO -- compute the likelihood of the data -- don't use the likelihood function above -- compute the negative sum of the log probabilities\n",
+        "  # TODO -- compute the negative log likelihood of the data without using a product\n",
+        "  # In other words, compute minus one times the sum of the log probabilities\n",
         "  # Equation 5.4 in the notes\n",
         "  # You will need np.sum(), np.log()\n",
         "  # Replace the line below\n",
@@ -329,7 +329,7 @@
         "mu_pred = shallow_nn(x_train, beta_0, omega_0, beta_1, omega_1)\n",
         "# Set the standard deviation to something reasonable\n",
         "sigma = 0.2\n",
-        "# Compute the log likelihood\n",
+        "# Compute the negative log likelihood\n",
         "nll = compute_negative_log_likelihood(y_train, mu_pred, sigma)\n",
         "# Let's double check we get the right answer before proceeding\n",
         "print(\"Correct answer = %9.9f, Your answer = %9.9f\"%(11.452419564,nll))"
@@ -352,7 +352,7 @@
     {
       "cell_type": "code",
       "source": [
-        "# Return the squared distance between the predicted\n",
+        "# Return the squared distance between the observed data (y_train) and the prediction of the model (y_pred)\n",
         "def compute_sum_of_squares(y_train, y_pred):\n",
         "  # TODO -- compute the sum of squared distances between the training data and the model prediction\n",
         "  # Eqn 5.10 in the notes.  Make sure that you understand this, and ask questions if you don't\n",
@@ -372,9 +372,9 @@
       "source": [
         "# Let's test this again\n",
         "beta_0, omega_0, beta_1, omega_1 = get_parameters()\n",
-        "# Use our neural network to predict the mean of the Gaussian\n",
+        "# Use our neural network to predict the mean of the Gaussian, which is out best prediction of y\n",
-        "y_pred = shallow_nn(x_train, beta_0, omega_0, beta_1, omega_1)\n",
+        "y_pred = mu_pred = shallow_nn(x_train, beta_0, omega_0, beta_1, omega_1)\n",
-        "# Compute the log likelihood\n",
+        "# Compute the sum of squares\n",
         "sum_of_squares = compute_sum_of_squares(y_train, y_pred)\n",
         "# Let's double check we get the right answer before proceeding\n",
         "print(\"Correct answer = %9.9f, Your answer = %9.9f\"%(2.020992572,sum_of_squares))"
@@ -388,7 +388,7 @@
     {
       "cell_type": "markdown",
       "source": [
-        "Now let's investigate finding the maximum likelihood / minimum log likelihood / least squares solution.  For simplicity, we'll assume that all the parameters are correct except one and look at how the likelihood, log likelihood, and sum of squares change as we manipulate the last parameter.  We'll start with overall y offset, beta_1 (formerly phi_0)"
+        "Now let's investigate finding the maximum likelihood / minimum negative log likelihood / least squares solution.  For simplicity, we'll assume that all the parameters are correct except one and look at how the likelihood, negative log likelihood, and sum of squares change as we manipulate the last parameter.  We'll start with overall y offset, beta_1 (formerly phi_0)"
       ],
       "metadata": {
         "id": "OgcRojvPWh4V"
@@ -431,13 +431,26 @@
     {
       "cell_type": "code",
       "source": [
-        "# Now let's plot the likelihood, negative log likelihood, and least squares as a function the value of the offset beta1\n",
+        "# Now let's plot the likelihood, negative log likelihood, and least squares as a function of the value of the offset beta1\n",
-        "fig, ax = plt.subplots(1,3)\n",
+        "fig, ax = plt.subplots(1,2)\n",
-        "fig.set_size_inches(10.5, 3.5)\n",
+        "fig.set_size_inches(10.5, 5.5)\n",
-        "fig.tight_layout(pad=3.0)\n",
+        "fig.tight_layout(pad=10.0)\n",
-        "ax[0].plot(beta_1_vals, likelihoods); ax[0].set_xlabel('beta_1[0]$'); ax[0].set_ylabel('likelihood')\n",
+        "likelihood_color = 'tab:red'\n",
-        "ax[1].plot(beta_1_vals, nlls); ax[1].set_xlabel('beta_1[0]'); ax[1].set_ylabel('negative log likelihood')\n",
+        "nll_color = 'tab:blue'\n",
-        "ax[2].plot(beta_1_vals, sum_squares); ax[2].set_xlabel('beta_1[0]'); ax[2].set_ylabel('sum of squares')\n",
+        "\n",
+        "ax[0].set_xlabel('beta_1[0]')\n",
+        "ax[0].set_ylabel('likelihood', color = likelihood_color)\n",
+        "ax[0].plot(beta_1_vals, likelihoods, color = likelihood_color)\n",
+        "ax[0].tick_params(axis='y', labelcolor=likelihood_color)\n",
+        "\n",
+        "ax00 = ax[0].twinx()\n",
+        "ax00.plot(beta_1_vals, nlls, color = nll_color)\n",
+        "ax00.set_ylabel('negative log likelihood', color = nll_color)\n",
+        "ax00.tick_params(axis='y', labelcolor = nll_color)\n",
+        "\n",
+        "plt.axvline(x = beta_1_vals[np.argmax(likelihoods)], linestyle='dotted')\n",
+        "\n",
+        "ax[1].plot(beta_1_vals, sum_squares); ax[1].set_xlabel('beta_1[0]'); ax[1].set_ylabel('sum of squares')\n",
         "plt.show()"
       ],
       "metadata": {
@@ -517,13 +530,27 @@
     {
       "cell_type": "code",
       "source": [
-        "# Now let's plot the likelihood, negative log likelihood, and least squares as a function the value of the standard divation sigma\n",
+        "# Now let's plot the likelihood, negative log likelihood, and least squares as a function of the value of the standard deviation sigma\n",
-        "fig, ax = plt.subplots(1,3)\n",
+        "fig, ax = plt.subplots(1,2)\n",
-        "fig.set_size_inches(10.5, 3.5)\n",
+        "fig.set_size_inches(10.5, 5.5)\n",
-        "fig.tight_layout(pad=3.0)\n",
+        "fig.tight_layout(pad=10.0)\n",
-        "ax[0].plot(sigma_vals, likelihoods); ax[0].set_xlabel('$\\sigma$'); ax[0].set_ylabel('likelihood')\n",
+        "likelihood_color = 'tab:red'\n",
-        "ax[1].plot(sigma_vals, nlls); ax[1].set_xlabel('$\\sigma$'); ax[1].set_ylabel('negative log likelihood')\n",
+        "nll_color = 'tab:blue'\n",
-        "ax[2].plot(sigma_vals, sum_squares); ax[2].set_xlabel('$\\sigma$'); ax[2].set_ylabel('sum of squares')\n",
+        "\n",
+        "\n",
+        "ax[0].set_xlabel('sigma')\n",
+        "ax[0].set_ylabel('likelihood', color = likelihood_color)\n",
+        "ax[0].plot(sigma_vals, likelihoods, color = likelihood_color)\n",
+        "ax[0].tick_params(axis='y', labelcolor=likelihood_color)\n",
+        "\n",
+        "ax00 = ax[0].twinx()\n",
+        "ax00.plot(sigma_vals, nlls, color = nll_color)\n",
+        "ax00.set_ylabel('negative log likelihood', color = nll_color)\n",
+        "ax00.tick_params(axis='y', labelcolor = nll_color)\n",
+        "\n",
+        "plt.axvline(x = sigma_vals[np.argmax(likelihoods)], linestyle='dotted')\n",
+        "\n",
+        "ax[1].plot(sigma_vals, sum_squares); ax[1].set_xlabel('sigma'); ax[1].set_ylabel('sum of squares')\n",
         "plt.show()"
       ],
       "metadata": {
@@ -538,8 +565,8 @@
         "# Hopefully, you can see that the maximum of the likelihood fn is at the same position as the minimum negative log likelihood\n",
         "# The least squares solution does not depend on sigma, so it's just flat -- no use here.\n",
         "# Let's check that:\n",
-        "print(\"Maximum likelihood = %3.3f, at beta_1=%3.3f\"%( (likelihoods[np.argmax(likelihoods)],sigma_vals[np.argmax(likelihoods)])))\n",
+        "print(\"Maximum likelihood = %3.3f, at sigma=%3.3f\"%( (likelihoods[np.argmax(likelihoods)],sigma_vals[np.argmax(likelihoods)])))\n",
-        "print(\"Minimum negative log likelihood = %3.3f, at beta_1=%3.3f\"%( (nlls[np.argmin(nlls)],sigma_vals[np.argmin(nlls)])))\n",
+        "print(\"Minimum negative log likelihood = %3.3f, at sigma=%3.3f\"%( (nlls[np.argmin(nlls)],sigma_vals[np.argmin(nlls)])))\n",
         "# Plot the best model\n",
         "sigma= sigma_vals[np.argmin(nlls)]\n",
         "y_model = shallow_nn(x_model, beta_0, omega_0, beta_1, omega_1)\n",
@@ -554,7 +581,7 @@
     {
       "cell_type": "markdown",
       "source": [
-        "Obviously, to fit the full neural model we would vary all of the 10 parameters of the network in the $\\boldsymbol\\beta_{0},\\boldsymbol\\omega_{0},\\boldsymbol\\beta_{1},\\boldsymbol\\omega_{1}$ (and maybe $\\sigma$) until we find the combination that have the maximum likelihood / minimum negative log likelihood / least squares.<br><br>\n",
+        "Obviously, to fit the full neural model we would vary all of the 10 parameters of the network in $\\boldsymbol\\beta_{0},\\boldsymbol\\Omega_{0},\\boldsymbol\\beta_{1},\\boldsymbol\\Omega_{1}$ (and maybe $\\sigma$) until we find the combination that have the maximum likelihood / minimum negative log likelihood / least squares.<br><br>\n",
         "\n",
         "Here we just varied one at a time as it is easier to see what is going on.  This is known as **coordinate descent**.\n"
       ],
@@ -563,4 +590,4 @@
       }
     }
   ]
-}
+}

Notebooks/Chap05/5_2_Binary_Cross_Entropy_Loss.ipynb

@@ -4,7 +4,7 @@
   "metadata": {
     "colab": {
       "provenance": [],
-      "authorship_tag": "ABX9TyOlPP7m+YTLyMPaN0WxRdrb",
+      "authorship_tag": "ABX9TyOSb+W2AOFVQm8FZcHAb2Jq",
       "include_colab_link": true
     },
     "kernelspec": {
@@ -66,7 +66,7 @@
         "  return activation\n",
         "\n",
         "# Define a shallow neural network\n",
-        "def shallow_nn(x, beta_0, omega_0, beta_1, omaga_1):\n",
+        "def shallow_nn(x, beta_0, omega_0, beta_1, omega_1):\n",
         "    # Make sure that input data is (1 x n_data) array\n",
         "    n_data = x.size\n",
         "    x = np.reshape(x,(1,n_data))\n",
@@ -378,12 +378,25 @@
     {
       "cell_type": "code",
       "source": [
-        "# Now let's plot the likelihood, and negative log likelihoods as a function the value of the offset beta1\n",
+        "# Now let's plot the likelihood, negative log likelihood, and least squares as a function the value of the offset beta1\n",
-        "fig, ax = plt.subplots(1,2)\n",
+        "fig, ax = plt.subplots()\n",
-        "fig.set_size_inches(10.5, 3.5)\n",
+        "fig.tight_layout(pad=5.0)\n",
-        "fig.tight_layout(pad=3.0)\n",
+        "likelihood_color = 'tab:red'\n",
-        "ax[0].plot(beta_1_vals, likelihoods); ax[0].set_xlabel('beta_1[0]'); ax[0].set_ylabel('likelihood')\n",
+        "nll_color = 'tab:blue'\n",
-        "ax[1].plot(beta_1_vals, nlls); ax[1].set_xlabel('beta_1[0]'); ax[1].set_ylabel('negative log likelihood')\n",
+        "\n",
+        "\n",
+        "ax.set_xlabel('beta_1[0]')\n",
+        "ax.set_ylabel('likelihood', color = likelihood_color)\n",
+        "ax.plot(beta_1_vals, likelihoods, color = likelihood_color)\n",
+        "ax.tick_params(axis='y', labelcolor=likelihood_color)\n",
+        "\n",
+        "ax1 = ax.twinx()\n",
+        "ax1.plot(beta_1_vals, nlls, color = nll_color)\n",
+        "ax1.set_ylabel('negative log likelihood', color = nll_color)\n",
+        "ax1.tick_params(axis='y', labelcolor = nll_color)\n",
+        "\n",
+        "plt.axvline(x = beta_1_vals[np.argmax(likelihoods)], linestyle='dotted')\n",
+        "\n",
         "plt.show()"
       ],
       "metadata": {
@@ -425,4 +438,4 @@
       }
     }
   ]
-}
+}

Notebooks/Chap05/5_3_Multiclass_Cross_entropy_Loss.ipynb

@@ -1,33 +1,22 @@
 {
-  "nbformat": 4,
-  "nbformat_minor": 0,
-  "metadata": {
-    "colab": {
-      "provenance": [],
-      "authorship_tag": "ABX9TyOVTohDBtmCCzSEqLJ4J9R/",
-      "include_colab_link": true
-    },
-    "kernelspec": {
-      "name": "python3",
-      "display_name": "Python 3"
-    },
-    "language_info": {
-      "name": "python"
-    }
-  },
   "cells": [
     {
+      "attachments": {},
       "cell_type": "markdown",
       "metadata": {
-        "id": "view-in-github",
+        "colab_type": "text",
-        "colab_type": "text"
+        "id": "view-in-github"
       },
       "source": [
         "<a href=\"https://colab.research.google.com/github/udlbook/udlbook/blob/main/Notebooks/Chap05/5_3_Multiclass_Cross_entropy_Loss.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
       ]
     },
     {
+      "attachments": {},
       "cell_type": "markdown",
+      "metadata": {
+        "id": "jSlFkICHwHQF"
+      },
       "source": [
         "# **Notebook 5.3 Multiclass Cross-Entropy Loss**\n",
         "\n",
@@ -36,10 +25,7 @@
         "Work through the cells below, running each cell in turn. In various places you will see the words \"TO DO\". Follow the instructions at these places and make predictions about what is going to happen or write code to complete the functions.\n",
         "\n",
         "Contact me at udlbookmail@gmail.com if you find any mistakes or have any suggestions."
-      ],
+      ]
-      "metadata": {
-        "id": "jSlFkICHwHQF"
-      }
     },
     {
       "cell_type": "code",
@@ -61,6 +47,11 @@
     },
     {
       "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "Fv7SZR3tv7mV"
+      },
+      "outputs": [],
       "source": [
         "# Define the Rectified Linear Unit (ReLU) function\n",
         "def ReLU(preactivation):\n",
@@ -68,7 +59,7 @@
         "  return activation\n",
         "\n",
         "# Define a shallow neural network\n",
-        "def shallow_nn(x, beta_0, omega_0, beta_1, omaga_1):\n",
+        "def shallow_nn(x, beta_0, omega_0, beta_1, omega_1):\n",
         "    # Make sure that input data is (1 x n_data) array\n",
         "    n_data = x.size\n",
         "    x = np.reshape(x,(1,n_data))\n",
@@ -77,15 +68,15 @@
         "    h1 = ReLU(np.matmul(beta_0,np.ones((1,n_data))) + np.matmul(omega_0,x))\n",
         "    model_out = np.matmul(beta_1,np.ones((1,n_data))) + np.matmul(omega_1,h1)\n",
         "    return model_out"
-      ],
+      ]
-      "metadata": {
-        "id": "Fv7SZR3tv7mV"
-      },
-      "execution_count": null,
-      "outputs": []
     },
     {
       "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "pUT9Ain_HRim"
+      },
+      "outputs": [],
       "source": [
         "# Get parameters for model -- we can call this function to easily reset them\n",
         "def get_parameters():\n",
@@ -103,15 +94,15 @@
         "  omega_1[2,0] = 16.0; omega_1[2,1] = -8.0; omega_1[2,2] =-8\n",
         "\n",
         "  return beta_0, omega_0, beta_1, omega_1"
-      ],
+      ]
-      "metadata": {
-        "id": "pUT9Ain_HRim"
-      },
-      "execution_count": null,
-      "outputs": []
     },
     {
       "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "NRR67ri_1TzN"
+      },
+      "outputs": [],
       "source": [
         "# Utility function for plotting data\n",
         "def plot_multiclass_classification(x_model, out_model, lambda_model, x_data = None, y_data = None, title= None):\n",
@@ -148,26 +139,27 @@
         "      if y_data[i] ==2:\n",
         "        ax[1].plot(x_data[i],-0.05, 'b.')\n",
         "  plt.show()"
-      ],
+      ]
-      "metadata": {
-        "id": "NRR67ri_1TzN"
-      },
-      "execution_count": null,
-      "outputs": []
     },
     {
+      "attachments": {},
       "cell_type": "markdown",
+      "metadata": {
+        "id": "PsgLZwsPxauP"
+      },
       "source": [
         "# Multiclass classification\n",
         "\n",
         "For multiclass classification, the network must predict the probability of $K$ classes, using $K$ outputs.  However, these probability must be non-negative and sum to one, and the network outputs can take arbitrary values.  Hence, we pass the outputs through a softmax function which maps $K$ arbitrary values to $K$ non-negative values that sum to one."
-      ],
+      ]
-      "metadata": {
-        "id": "PsgLZwsPxauP"
-      }
     },
     {
       "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "uFb8h-9IXnIe"
+      },
+      "outputs": [],
       "source": [
         "# Softmax function that maps a vector of arbitrary values to a vector of values that are positive and sum to one.\n",
         "def softmax(model_out):\n",
@@ -184,15 +176,15 @@
         "  softmax_model_out = np.ones_like(model_out)/ exp_model_out.shape[0]\n",
         "\n",
         "  return softmax_model_out"
-      ],
+      ]
-      "metadata": {
-        "id": "uFb8h-9IXnIe"
-      },
-      "execution_count": null,
-      "outputs": []
     },
     {
       "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "VWzNOt1swFVd"
+      },
+      "outputs": [],
       "source": [
         "\n",
         "# Let's create some 1D training data\n",
@@ -214,62 +206,64 @@
         "model_out= shallow_nn(x_model, beta_0, omega_0, beta_1, omega_1)\n",
         "lambda_model = softmax(model_out)\n",
         "plot_multiclass_classification(x_model, model_out, lambda_model, x_train, y_train)\n"
-      ],
+      ]
-      "metadata": {
-        "id": "VWzNOt1swFVd"
-      },
-      "execution_count": null,
-      "outputs": []
     },
     {
+      "attachments": {},
       "cell_type": "markdown",
-      "source": [
-        "The left is model output and the right is the model output after the softmax has been applied, so it now lies in the range [0,1] and represents the probability, that y=0 (red), 1 (green) and 2 (blue)   The dots at the bottom show the training data with the same color scheme.  So we want the red curve to be high where there are red dots, the green curve to be high where there are green dots, and the blue curve to be high where there are blue dots  We'll compute the the likelihood and the negative log likelihood."
-      ],
       "metadata": {
         "id": "MvVX6tl9AEXF"
-      }
+      },
+      "source": [
+        "The left is model output and the right is the model output after the softmax has been applied, so it now lies in the range [0,1] and represents the probability, that y=0 (red), 1 (green) and 2 (blue)   The dots at the bottom show the training data with the same color scheme.  So we want the red curve to be high where there are red dots, the green curve to be high where there are green dots, and the blue curve to be high where there are blue dots  We'll compute the the likelihood and the negative log likelihood."
+      ]
     },
     {
       "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "YaLdRlEX0FkU"
+      },
+      "outputs": [],
       "source": [
         "# Return probability under Categorical distribution for input x\n",
         "# Just take value from row k of lambda param where y =k,\n",
         "def categorical_distribution(y, lambda_param):\n",
         "    return np.array([lambda_param[row, i] for i, row in enumerate (y)])"
-      ],
+      ]
-      "metadata": {
-        "id": "YaLdRlEX0FkU"
-      },
-      "execution_count": null,
-      "outputs": []
     },
     {
       "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "4TSL14dqHHbV"
+      },
+      "outputs": [],
       "source": [
         "# Let's double check we get the right answer before proceeding\n",
         "print(\"Correct answer = %3.3f, Your answer = %3.3f\"%(0.2,categorical_distribution(np.array([[0]]),np.array([[0.2],[0.5],[0.3]]))))\n",
         "print(\"Correct answer = %3.3f, Your answer = %3.3f\"%(0.5,categorical_distribution(np.array([[1]]),np.array([[0.2],[0.5],[0.3]]))))\n",
         "print(\"Correct answer = %3.3f, Your answer = %3.3f\"%(0.3,categorical_distribution(np.array([[2]]),np.array([[0.2],[0.5],[0.3]]))))\n",
         "\n"
-      ],
+      ]
-      "metadata": {
-        "id": "4TSL14dqHHbV"
-      },
-      "execution_count": null,
-      "outputs": []
     },
     {
+      "attachments": {},
       "cell_type": "markdown",
-      "source": [
-        "Now let's compute the likelihood using this function"
-      ],
       "metadata": {
         "id": "R5z_0dzQMF35"
-      }
+      },
+      "source": [
+        "Now let's compute the likelihood using this function"
+      ]
     },
     {
       "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "zpS7o6liCx7f"
+      },
+      "outputs": [],
       "source": [
         "# Return the likelihood of all of the data under the model\n",
         "def compute_likelihood(y_train, lambda_param):\n",
@@ -280,15 +274,15 @@
         "  likelihood = 0\n",
         "\n",
         "  return likelihood"
-      ],
+      ]
-      "metadata": {
-        "id": "zpS7o6liCx7f"
-      },
-      "execution_count": null,
-      "outputs": []
     },
     {
       "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "1hQxBLoVNlr2"
+      },
+      "outputs": [],
       "source": [
         "# Let's test this\n",
         "beta_0, omega_0, beta_1, omega_1 = get_parameters()\n",
@@ -299,27 +293,28 @@
         "likelihood = compute_likelihood(y_train, lambda_train)\n",
         "# Let's double check we get the right answer before proceeding\n",
         "print(\"Correct answer = %9.9f, Your answer = %9.9f\"%(0.000000041,likelihood))"
-      ],
+      ]
-      "metadata": {
-        "id": "1hQxBLoVNlr2"
-      },
-      "execution_count": null,
-      "outputs": []
     },
     {
+      "attachments": {},
       "cell_type": "markdown",
+      "metadata": {
+        "id": "HzphKgPfOvlk"
+      },
       "source": [
         "You can see that this gives a very small answer, even for this small 1D dataset, and with the model fitting quite well.  This is because it is the product of several probabilities, which are all quite small themselves.\n",
         "This will get out of hand pretty quickly with real datasets -- the likelihood will get so small that we can't represent it with normal finite-precision math\n",
         "\n",
         "This is why we use negative log likelihood"
-      ],
+      ]
-      "metadata": {
-        "id": "HzphKgPfOvlk"
-      }
     },
     {
       "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "dsT0CWiKBmTV"
+      },
+      "outputs": [],
       "source": [
         "# Return the negative log likelihood of the data under the model\n",
         "def compute_negative_log_likelihood(y_train, lambda_param):\n",
@@ -329,15 +324,15 @@
         "  nll = 0\n",
         "\n",
         "  return nll"
-      ],
+      ]
-      "metadata": {
-        "id": "dsT0CWiKBmTV"
-      },
-      "execution_count": null,
-      "outputs": []
     },
     {
       "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "nVxUXg9rQmwI"
+      },
+      "outputs": [],
       "source": [
         "# Let's test this\n",
         "beta_0, omega_0, beta_1, omega_1 = get_parameters()\n",
@@ -349,24 +344,25 @@
         "nll = compute_negative_log_likelihood(y_train, lambda_train)\n",
         "# Let's double check we get the right answer before proceeding\n",
         "print(\"Correct answer = %9.9f, Your answer = %9.9f\"%(17.015457867,nll))"
-      ],
+      ]
-      "metadata": {
-        "id": "nVxUXg9rQmwI"
-      },
-      "execution_count": null,
-      "outputs": []
     },
     {
+      "attachments": {},
       "cell_type": "markdown",
-      "source": [
-        "Now let's investigate finding the maximum likelihood / minimum log likelihood solution.  For simplicity, we'll assume that all the parameters are fixed except one and look at how the likelihood and log likelihood change as we manipulate the last parameter.  We'll start with overall y_offset, beta_1 (formerly phi_0)"
-      ],
       "metadata": {
         "id": "OgcRojvPWh4V"
-      }
+      },
+      "source": [
+        "Now let's investigate finding the maximum likelihood / minimum log likelihood solution.  For simplicity, we'll assume that all the parameters are fixed except one and look at how the likelihood and log likelihood change as we manipulate the last parameter.  We'll start with overall y_offset, $\\beta_1$ (formerly $\\phi_0$)"
+      ]
     },
     {
       "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "pFKtDaAeVU4U"
+      },
+      "outputs": [],
       "source": [
         "# Define a range of values for the parameter\n",
         "beta_1_vals = np.arange(-2,6.0,0.1)\n",
@@ -391,32 +387,45 @@
         "    model_out = shallow_nn(x_model, beta_0, omega_0, beta_1, omega_1)\n",
         "    lambda_model = softmax(model_out)\n",
         "    plot_multiclass_classification(x_model, model_out, lambda_model, x_train, y_train, title=\"beta1[0,0]=%3.3f\"%(beta_1[0,0]))\n"
-      ],
+      ]
-      "metadata": {
-        "id": "pFKtDaAeVU4U"
-      },
-      "execution_count": null,
-      "outputs": []
     },
     {
       "cell_type": "code",
-      "source": [
+      "execution_count": null,
-        "# Now let's plot the likelihood, negative log likelihood as a function the value of the offset beta1\n",
-        "fig, ax = plt.subplots(1,2)\n",
-        "fig.set_size_inches(10.5, 3.5)\n",
-        "fig.tight_layout(pad=3.0)\n",
-        "ax[0].plot(beta_1_vals, likelihoods); ax[0].set_xlabel('beta_1[0,0]'); ax[0].set_ylabel('likelihood')\n",
-        "ax[1].plot(beta_1_vals, nlls); ax[1].set_xlabel('beta_1[0,0]'); ax[1].set_ylabel('negative log likelihood')\n",
-        "plt.show()"
-      ],
       "metadata": {
         "id": "UHXeTa9MagO6"
       },
-      "execution_count": null,
+      "outputs": [],
-      "outputs": []
+      "source": [
+        "# Now let's plot the likelihood, negative log likelihood, and least squares as a function the value of the offset beta1\n",
+        "fig, ax = plt.subplots()\n",
+        "fig.tight_layout(pad=5.0)\n",
+        "likelihood_color = 'tab:red'\n",
+        "nll_color = 'tab:blue'\n",
+        "\n",
+        "\n",
+        "ax.set_xlabel('beta_1[0, 0]')\n",
+        "ax.set_ylabel('likelihood', color = likelihood_color)\n",
+        "ax.plot(beta_1_vals, likelihoods, color = likelihood_color)\n",
+        "ax.tick_params(axis='y', labelcolor=likelihood_color)\n",
+        "\n",
+        "ax1 = ax.twinx()\n",
+        "ax1.plot(beta_1_vals, nlls, color = nll_color)\n",
+        "ax1.set_ylabel('negative log likelihood', color = nll_color)\n",
+        "ax1.tick_params(axis='y', labelcolor = nll_color)\n",
+        "\n",
+        "plt.axvline(x = beta_1_vals[np.argmax(likelihoods)], linestyle='dotted')\n",
+        "\n",
+        "plt.show()"
+      ]
     },
     {
       "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "aDEPhddNdN4u"
+      },
+      "outputs": [],
       "source": [
         "# Hopefully, you can see that the maximum of the likelihood fn is at the same position as the minimum negative log likelihood solution\n",
         "# Let's check that:\n",
@@ -428,24 +437,36 @@
         "model_out = shallow_nn(x_model, beta_0, omega_0, beta_1, omega_1)\n",
         "lambda_model = softmax(model_out)\n",
         "plot_multiclass_classification(x_model, model_out, lambda_model, x_train, y_train, title=\"beta1[0,0]=%3.3f\"%(beta_1[0,0]))\n"
-      ],
+      ]
-      "metadata": {
-        "id": "aDEPhddNdN4u"
-      },
-      "execution_count": null,
-      "outputs": []
     },
     {
+      "attachments": {},
       "cell_type": "markdown",
+      "metadata": {
+        "id": "771G8N1Vk5A2"
+      },
       "source": [
         "They both give the same answer. But you can see from the likelihood above that the likelihood is very small unless the parameters are almost correct.  So in practice, we would work with the negative log likelihood.<br><br>\n",
         "\n",
         "Again, to fit the full neural model we would vary all of the 16 parameters of the network in the $\\boldsymbol\\beta_{0},\\boldsymbol\\omega_{0},\\boldsymbol\\beta_{1},\\boldsymbol\\omega_{1}$ until we find the combination that have the maximum likelihood / minimum negative log likelihood.<br><br>\n",
         "\n"
-      ],
+      ]
-      "metadata": {
-        "id": "771G8N1Vk5A2"
-      }
     }
-  ]
+  ],
-}
+  "metadata": {
+    "colab": {
+      "authorship_tag": "ABX9TyOPv/l+ToaApJV7Nz+8AtpV",
+      "include_colab_link": true,
+      "provenance": []
+    },
+    "kernelspec": {
+      "display_name": "Python 3",
+      "name": "python3"
+    },
+    "language_info": {
+      "name": "python"
+    }
+  },
+  "nbformat": 4,
+  "nbformat_minor": 0
+}

Notebooks/Chap06/6_1_Line_Search.ipynb

@@ -4,7 +4,7 @@
   "metadata": {
     "colab": {
       "provenance": [],
-      "authorship_tag": "ABX9TyOfxeJ15PMkIi4geDTRCz3c",
+      "authorship_tag": "ABX9TyN4E9Vtuk6t2BhZ0Ajv5SW3",
       "include_colab_link": true
     },
     "kernelspec": {
@@ -131,14 +131,15 @@
         "\n",
         "        print('Iter %d, a=%3.3f, b=%3.3f, c=%3.3f, d=%3.3f'%(n_iter, a,b,c,d))\n",
         "\n",
-        "        # Rule #1 If point A is less than points B, C, and D then halve values of B, C, and D\n",
+        "        # Rule #1 If the HEIGHT at point A is less the HEIGHT at points B, C, and D then halve values of B, C, and D\n",
+        "        # i.e. bring them closer to the original point\n",
         "        # i.e. bring them closer to the original point\n",
         "        # TODO REPLACE THE BLOCK OF CODE BELOW WITH THIS RULE\n",
         "        if (0):\n",
         "          continue;\n",
         "\n",
         "\n",
-        "        # Rule #2 If point b is less than point c then\n",
+        "        # Rule #2 If the HEIGHT at point b is less than the HEIGHT at point c then\n",
         "        #                     then point d becomes point c, and\n",
         "        #                     point b becomes 1/3 between a and new d\n",
         "        #                     point c becomes 2/3 between a and new d\n",
@@ -146,7 +147,7 @@
         "        if (0):\n",
         "          continue;\n",
         "\n",
-        "        # Rule #3 If point c is less than point b then\n",
+        "        # Rule #3 If the HEIGHT at point c is less than the HEIGHT at point b then\n",
         "        #                     then point a becomes point b, and\n",
         "        #                     point b becomes 1/3 between new a and d\n",
         "        #                     point c becomes 2/3 between new a and d\n",

Notebooks/Chap06/6_2_Gradient_Descent.ipynb

@@ -1,46 +1,32 @@
 {
-  "nbformat": 4,
-  "nbformat_minor": 0,
-  "metadata": {
-    "colab": {
-      "provenance": [],
-      "authorship_tag": "ABX9TyM/FIXDTd6tZYs6WRzK00hB",
-      "include_colab_link": true
-    },
-    "kernelspec": {
-      "name": "python3",
-      "display_name": "Python 3"
-    },
-    "language_info": {
-      "name": "python"
-    }
-  },
   "cells": [
     {
+      "attachments": {},
       "cell_type": "markdown",
       "metadata": {
-        "id": "view-in-github",
+        "colab_type": "text",
-        "colab_type": "text"
+        "id": "view-in-github"
       },
       "source": [
         "<a href=\"https://colab.research.google.com/github/udlbook/udlbook/blob/main/Notebooks/Chap06/6_2_Gradient_Descent.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
       ]
     },
     {
+      "attachments": {},
       "cell_type": "markdown",
+      "metadata": {
+        "id": "el8l05WQEO46"
+      },
       "source": [
         "# **Notebook 6.2 Gradient descent**\n",
         "\n",
-        "This notebook recreates the gradient descent algorithm as shon in figure 6.1.\n",
+        "This notebook recreates the gradient descent algorithm as shown in figure 6.1.\n",
         "\n",
         "Work through the cells below, running each cell in turn. In various places you will see the words \"TO DO\". Follow the instructions at these places and make predictions about what is going to happen or write code to complete the functions.\n",
         "\n",
         "Contact me at udlbookmail@gmail.com if you find any mistakes or have any suggestions.\n",
         "\n"
-      ],
+      ]
-      "metadata": {
-        "id": "el8l05WQEO46"
-      }
     },
     {
       "cell_type": "code",
@@ -59,34 +45,39 @@
     },
     {
       "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "4cRkrh9MZ58Z"
+      },
+      "outputs": [],
       "source": [
         "# Let's create our training data 12 pairs {x_i, y_i}\n",
         "# We'll try to fit the straight line model to these data\n",
         "data = np.array([[0.03,0.19,0.34,0.46,0.78,0.81,1.08,1.18,1.39,1.60,1.65,1.90],\n",
         "                 [0.67,0.85,1.05,1.00,1.40,1.50,1.30,1.54,1.55,1.68,1.73,1.60]])"
-      ],
+      ]
-      "metadata": {
-        "id": "4cRkrh9MZ58Z"
-      },
-      "execution_count": null,
-      "outputs": []
     },
     {
       "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "WQUERmb2erAe"
+      },
+      "outputs": [],
       "source": [
         "# Let's define our model -- just a straight line with intercept phi[0] and slope phi[1]\n",
         "def model(phi,x):\n",
         "  y_pred = phi[0]+phi[1] * x\n",
         "  return y_pred"
-      ],
+      ]
-      "metadata": {
-        "id": "WQUERmb2erAe"
-      },
-      "execution_count": null,
-      "outputs": []
     },
     {
       "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "qFRe9POHF2le"
+      },
+      "outputs": [],
       "source": [
         "# Draw model\n",
         "def draw_model(data,model,phi,title=None):\n",
@@ -102,39 +93,40 @@
         "  if title is not None:\n",
         "    ax.set_title(title)\n",
         "  plt.show()"
-      ],
+      ]
-      "metadata": {
-        "id": "qFRe9POHF2le"
-      },
-      "execution_count": null,
-      "outputs": []
     },
     {
       "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "TXx1Tpd1Tl-I"
+      },
+      "outputs": [],
       "source": [
         "# Initialize the parameters to some arbitrary values and draw the model\n",
         "phi = np.zeros((2,1))\n",
         "phi[0] = 0.6      # Intercept\n",
         "phi[1] = -0.2      # Slope\n",
         "draw_model(data,model,phi, \"Initial parameters\")\n"
-      ],
+      ]
-      "metadata": {
-        "id": "TXx1Tpd1Tl-I"
-      },
-      "execution_count": null,
-      "outputs": []
     },
     {
+      "attachments": {},
       "cell_type": "markdown",
-      "source": [
-        "Now lets create compute the sum of squares loss for the training data"
-      ],
       "metadata": {
         "id": "QU5mdGvpTtEG"
-      }
+      },
+      "source": [
+        "Now lets create compute the sum of squares loss for the training data"
+      ]
     },
     {
       "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "I7dqTY2Gg7CR"
+      },
+      "outputs": [],
       "source": [
         "def compute_loss(data_x, data_y, model, phi):\n",
         "  # TODO -- Write this function -- replace the line below\n",
@@ -145,45 +137,47 @@
         "  loss = 0\n",
         "\n",
         "  return loss"
-      ],
+      ]
-      "metadata": {
-        "id": "I7dqTY2Gg7CR"
-      },
-      "execution_count": null,
-      "outputs": []
     },
     {
+      "attachments": {},
       "cell_type": "markdown",
-      "source": [
-        "Let's just test that we got that right"
-      ],
       "metadata": {
         "id": "eB5DQvU5hYNx"
-      }
+      },
+      "source": [
+        "Let's just test that we got that right"
+      ]
     },
     {
       "cell_type": "code",
-      "source": [
+      "execution_count": null,
-        "loss = compute_loss(data[0,:],data[1,:],model,np.array([[0.6],[-0.2]]))\n",
-        "print('Your loss = %3.3f, Correct loss = %3.3f'%(loss, 12.367))"
-      ],
       "metadata": {
         "id": "Ty05UtEEg9tc"
       },
-      "execution_count": null,
+      "outputs": [],
-      "outputs": []
+      "source": [
+        "loss = compute_loss(data[0,:],data[1,:],model,np.array([[0.6],[-0.2]]))\n",
+        "print('Your loss = %3.3f, Correct loss = %3.3f'%(loss, 12.367))"
+      ]
     },
     {
+      "attachments": {},
       "cell_type": "markdown",
-      "source": [
-        "Now let's plot the whole loss function"
-      ],
       "metadata": {
         "id": "F3trnavPiHpH"
-      }
+      },
+      "source": [
+        "Now let's plot the whole loss function"
+      ]
     },
     {
       "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "K-NTHpAAHlCl"
+      },
+      "outputs": [],
       "source": [
         "def draw_loss_function(compute_loss, data,  model, phi_iters = None):\n",
         "  # Define pretty colormap\n",
@@ -210,39 +204,40 @@
         "  ax.set_ylim([1,-1])\n",
         "  ax.set_xlabel('Intercept $\\phi_{0}$'); ax.set_ylabel('Slope, $\\phi_{1}$')\n",
         "  plt.show()"
-      ],
+      ]
-      "metadata": {
-        "id": "K-NTHpAAHlCl"
-      },
-      "execution_count": null,
-      "outputs": []
     },
     {
       "cell_type": "code",
-      "source": [
+      "execution_count": null,
-        "draw_loss_function(compute_loss, data, model)"
-      ],
       "metadata": {
         "id": "l8HbvIupnTME"
       },
-      "execution_count": null,
+      "outputs": [],
-      "outputs": []
+      "source": [
+        "draw_loss_function(compute_loss, data, model)"
+      ]
     },
     {
+      "attachments": {},
       "cell_type": "markdown",
+      "metadata": {
+        "id": "s9Duf05WqqSC"
+      },
       "source": [
         "Now let's compute the gradient vector for a given set of parameters:\n",
         "\n",
         "\\begin{equation}\n",
         "\\frac{\\partial L}{\\partial \\boldsymbol\\phi} = \\begin{bmatrix}\\frac{\\partial L}{\\partial \\phi_0} \\\\\\frac{\\partial L}{\\partial \\phi_1} \\end{bmatrix}.\n",
         "\\end{equation}"
-      ],
+      ]
-      "metadata": {
-        "id": "s9Duf05WqqSC"
-      }
     },
     {
       "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "UpswmkL2qwBT"
+      },
+      "outputs": [],
       "source": [
         "# These are in the lecture slides and notes, but worth trying to calculate them yourself to\n",
         "# check that you get them right.  Write out the expression for the sum of squares loss and take the\n",
@@ -254,31 +249,32 @@
         "\n",
         "    # Return the gradient\n",
         "    return np.array([[dl_dphi0],[dl_dphi1]])"
-      ],
+      ]
-      "metadata": {
-        "id": "UpswmkL2qwBT"
-      },
-      "execution_count": null,
-      "outputs": []
     },
     {
+      "attachments": {},
       "cell_type": "markdown",
+      "metadata": {
+        "id": "RS1nEcYVuEAM"
+      },
       "source": [
         "We can check we got this right using a trick known as **finite differences**.  If we evaluate the function and then change one of the parameters by a very small amount and normalize by that amount, we get an approximation to the gradient, so:\n",
         "\n",
-        "\\begin{eqnarray}\n",
+        "\\begin{align}\n",
         "\\frac{\\partial L}{\\partial \\phi_{0}}&\\approx & \\frac{L[\\phi_0+\\delta, \\phi_1]-L[\\phi_0, \\phi_1]}{\\delta}\\\\\n",
         "\\frac{\\partial L}{\\partial \\phi_{1}}&\\approx & \\frac{L[\\phi_0, \\phi_1+\\delta]-L[\\phi_0, \\phi_1]}{\\delta}\n",
-        "\\end{eqnarray}\n",
+        "\\end{align}\n",
         "\n",
         "We can't do this when there are many parameters;  for a million parameters, we would have to evaluate the loss function two million times, and usually computing the gradients directly is much more efficient."
-      ],
+      ]
-      "metadata": {
-        "id": "RS1nEcYVuEAM"
-      }
     },
     {
       "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "QuwAHN7yt-gi"
+      },
+      "outputs": [],
       "source": [
         "# Compute the gradient using your function\n",
         "gradient = compute_gradient(data[0,:],data[1,:], phi)\n",
@@ -291,28 +287,29 @@
         "                    compute_loss(data[0,:],data[1,:],model,phi))/delta\n",
         "print(\"Approx gradients: (%3.3f,%3.3f)\"%(dl_dphi0_est,dl_dphi1_est))\n",
         "# There might be small differences in the last significant figure because finite gradients is an approximation\n"
-      ],
+      ]
-      "metadata": {
-        "id": "QuwAHN7yt-gi"
-      },
-      "execution_count": null,
-      "outputs": []
     },
     {
+      "attachments": {},
       "cell_type": "markdown",
-      "source": [
-        "Now we are ready to perform gradient descent.  We'll need to use our line search routine from part I, which I've reproduced here plus the helper function loss_function_1D that converts from a 2D problem to a 1D problem"
-      ],
       "metadata": {
         "id": "5EIjMM9Fw2eT"
-      }
+      },
+      "source": [
+        "Now we are ready to perform gradient descent.  We'll need to use our line search routine from notebook 6.1, which I've reproduced here plus the helper function loss_function_1D that maps the search along the negative gradient direction in 2D space to a 1D problem (distance along this direction)"
+      ]
     },
     {
       "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "XrJ2gQjfw1XP"
+      },
+      "outputs": [],
       "source": [
-        "def loss_function_1D(dist_prop, data, model, phi_start, gradient):\n",
+        "def loss_function_1D(dist_prop, data, model, phi_start, search_direction):\n",
         "  # Return the loss after moving this far\n",
-        "  return compute_loss(data[0,:], data[1,:], model, phi_start+ gradient * dist_prop)\n",
+        "  return compute_loss(data[0,:], data[1,:], model, phi_start+ search_direction * dist_prop)\n",
         "\n",
         "def line_search(data, model, phi, gradient, thresh=.00001, max_dist = 0.1, max_iter = 15, verbose=False):\n",
         "    # Initialize four points along the range we are going to search\n",
@@ -363,32 +360,32 @@
         "\n",
         "    # Return average of two middle points\n",
         "    return (b+c)/2.0"
-      ],
+      ]
-      "metadata": {
-        "id": "XrJ2gQjfw1XP"
-      },
-      "execution_count": null,
-      "outputs": []
     },
     {
       "cell_type": "code",
-      "source": [
+      "execution_count": null,
-        "def gradient_descent_step(phi, data,  model):\n",
-        "  # TODO -- update Phi with the gradient descent step (equation 6.3)\n",
-        "  # 1. Compute the gradient\n",
-        "  # 2. Find the best step size alpha (use negative gradient as going downhill)\n",
-        "  # 3. Update the parameters phi\n",
-        "\n",
-        "  return phi"
-      ],
       "metadata": {
         "id": "YVq6rmaWRD2M"
       },
-      "execution_count": null,
+      "outputs": [],
-      "outputs": []
+      "source": [
+        "def gradient_descent_step(phi, data,  model):\n",
+        "  # TODO -- update Phi with the gradient descent step (equation 6.3)\n",
+        "  # 1. Compute the gradient (you wrote this function above)\n",
+        "  # 2. Find the best step size alpha using line search function (above) -- use negative gradient as going downhill\n",
+        "  # 3. Update the parameters phi based on the gradient and the step size alpha.\n",
+        "\n",
+        "  return phi"
+      ]
     },
     {
       "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "tOLd0gtdRLLS"
+      },
+      "outputs": [],
       "source": [
         "# Initialize the parameters and draw the model\n",
         "n_steps = 10\n",
@@ -410,12 +407,22 @@
         "\n",
         "# Draw the trajectory on the loss function\n",
         "draw_loss_function(compute_loss, data, model,phi_all)\n"
-      ],
+      ]
-      "metadata": {
-        "id": "tOLd0gtdRLLS"
-      },
-      "execution_count": null,
-      "outputs": []
     }
-  ]
+  ],
-}
+  "metadata": {
+    "colab": {
+      "include_colab_link": true,
+      "provenance": []
+    },
+    "kernelspec": {
+      "display_name": "Python 3",
+      "name": "python3"
+    },
+    "language_info": {
+      "name": "python"
+    }
+  },
+  "nbformat": 4,
+  "nbformat_minor": 0
+}

Notebooks/Chap06/6_3_Stochastic_Gradient_Descent.ipynb

@@ -1,33 +1,22 @@
 {
-  "nbformat": 4,
-  "nbformat_minor": 0,
-  "metadata": {
-    "colab": {
-      "provenance": [],
-      "authorship_tag": "ABX9TyNk5FN4qlw3pk8BwDVWw1jN",
-      "include_colab_link": true
-    },
-    "kernelspec": {
-      "name": "python3",
-      "display_name": "Python 3"
-    },
-    "language_info": {
-      "name": "python"
-    }
-  },
   "cells": [
     {
+      "attachments": {},
       "cell_type": "markdown",
       "metadata": {
-        "id": "view-in-github",
+        "colab_type": "text",
-        "colab_type": "text"
+        "id": "view-in-github"
       },
       "source": [
         "<a href=\"https://colab.research.google.com/github/udlbook/udlbook/blob/main/Notebooks/Chap06/6_3_Stochastic_Gradient_Descent.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
       ]
     },
     {
+      "attachments": {},
       "cell_type": "markdown",
+      "metadata": {
+        "id": "el8l05WQEO46"
+      },
       "source": [
         "# **Notebook 6.3: Stochastic gradient descent**\n",
         "\n",
@@ -39,10 +28,7 @@
         "\n",
         "\n",
         "\n"
-      ],
+      ]
-      "metadata": {
-        "id": "el8l05WQEO46"
-      }
     },
     {
       "cell_type": "code",
@@ -61,6 +47,11 @@
     },
     {
       "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "4cRkrh9MZ58Z"
+      },
+      "outputs": [],
       "source": [
         "# Let's create our training data 30 pairs {x_i, y_i}\n",
         "# We'll try to fit the Gabor model to these data\n",
@@ -74,15 +65,15 @@
         "                  -2.365e-02,5.098e-01,-2.777e-01,3.367e-01,1.927e-01,-2.222e-01,\n",
         "                  6.352e-02,6.888e-03,3.224e-02,1.091e-02,-5.706e-01,-5.258e-02,\n",
         "                  -3.666e-02,1.709e-01,-4.805e-02,2.008e-01,-1.904e-01,5.952e-01]])"
-      ],
+      ]
-      "metadata": {
-        "id": "4cRkrh9MZ58Z"
-      },
-      "execution_count": null,
-      "outputs": []
     },
     {
       "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "WQUERmb2erAe"
+      },
+      "outputs": [],
       "source": [
         "# Let's define our model\n",
         "def model(phi,x):\n",
@@ -90,15 +81,15 @@
         "  gauss_component = np.exp(-(phi[0] + 0.06 * phi[1] * x) * (phi[0] + 0.06 * phi[1] * x) / 32)\n",
         "  y_pred= sin_component * gauss_component\n",
         "  return y_pred"
-      ],
+      ]
-      "metadata": {
-        "id": "WQUERmb2erAe"
-      },
-      "execution_count": null,
-      "outputs": []
     },
     {
       "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "qFRe9POHF2le"
+      },
+      "outputs": [],
       "source": [
         "# Draw model\n",
         "def draw_model(data,model,phi,title=None):\n",
@@ -113,39 +104,40 @@
         "  if title is not None:\n",
         "    ax.set_title(title)\n",
         "  plt.show()"
-      ],
+      ]
-      "metadata": {
-        "id": "qFRe9POHF2le"
-      },
-      "execution_count": null,
-      "outputs": []
     },
     {
       "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "TXx1Tpd1Tl-I"
+      },
+      "outputs": [],
       "source": [
-        "# Initialize the parmaeters and draw the model\n",
+        "# Initialize the parameters and draw the model\n",
         "phi = np.zeros((2,1))\n",
         "phi[0] =  -5     # Horizontal offset\n",
         "phi[1] =  25     # Frequency\n",
         "draw_model(data,model,phi, \"Initial parameters\")\n"
-      ],
+      ]
-      "metadata": {
-        "id": "TXx1Tpd1Tl-I"
-      },
-      "execution_count": null,
-      "outputs": []
     },
     {
+      "attachments": {},
       "cell_type": "markdown",
-      "source": [
-        "Now lets create compute the sum of squares loss for the training data"
-      ],
       "metadata": {
         "id": "QU5mdGvpTtEG"
-      }
+      },
+      "source": [
+        "Now lets create compute the sum of squares loss for the training data"
+      ]
     },
     {
       "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "I7dqTY2Gg7CR"
+      },
+      "outputs": [],
       "source": [
         "def compute_loss(data_x, data_y, model, phi):\n",
         "  # TODO -- Write this function -- replace the line below\n",
@@ -155,45 +147,47 @@
         "  loss = 0\n",
         "\n",
         "  return loss"
-      ],
+      ]
-      "metadata": {
-        "id": "I7dqTY2Gg7CR"
-      },
-      "execution_count": null,
-      "outputs": []
     },
     {
+      "attachments": {},
       "cell_type": "markdown",
-      "source": [
-        "Let's just test that we got that right"
-      ],
       "metadata": {
         "id": "eB5DQvU5hYNx"
-      }
+      },
+      "source": [
+        "Let's just test that we got that right"
+      ]
     },
     {
       "cell_type": "code",
-      "source": [
+      "execution_count": null,
-        "loss = compute_loss(data[0,:],data[1,:],model,np.array([[0.6],[-0.2]]))\n",
-        "print('Your loss = %3.3f, Correct loss = %3.3f'%(loss, 16.419))"
-      ],
       "metadata": {
         "id": "Ty05UtEEg9tc"
       },
-      "execution_count": null,
+      "outputs": [],
-      "outputs": []
+      "source": [
+        "loss = compute_loss(data[0,:],data[1,:],model,np.array([[0.6],[-0.2]]))\n",
+        "print('Your loss = %3.3f, Correct loss = %3.3f'%(loss, 16.419))"
+      ]
     },
     {
+      "attachments": {},
       "cell_type": "markdown",
-      "source": [
-        "Now let's plot the whole loss function"
-      ],
       "metadata": {
         "id": "F3trnavPiHpH"
-      }
+      },
+      "source": [
+        "Now let's plot the whole loss function"
+      ]
     },
     {
       "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "K-NTHpAAHlCl"
+      },
+      "outputs": [],
       "source": [
         "def draw_loss_function(compute_loss, data,  model, phi_iters = None):\n",
         "  # Define pretty colormap\n",
@@ -220,39 +214,40 @@
         "  ax.set_ylim([2.5,22.5])\n",
         "  ax.set_xlabel('Offset $\\phi_{0}$'); ax.set_ylabel('Frequency, $\\phi_{1}$')\n",
         "  plt.show()"
-      ],
+      ]
-      "metadata": {
-        "id": "K-NTHpAAHlCl"
-      },
-      "execution_count": null,
-      "outputs": []
     },
     {
       "cell_type": "code",
-      "source": [
+      "execution_count": null,
-        "draw_loss_function(compute_loss, data, model)"
-      ],
       "metadata": {
         "id": "l8HbvIupnTME"
       },
-      "execution_count": null,
+      "outputs": [],
-      "outputs": []
+      "source": [
+        "draw_loss_function(compute_loss, data, model)"
+      ]
     },
     {
+      "attachments": {},
       "cell_type": "markdown",
+      "metadata": {
+        "id": "s9Duf05WqqSC"
+      },
       "source": [
         "Now let's compute the gradient vector for a given set of parameters:\n",
         "\n",
         "\\begin{equation}\n",
         "\\frac{\\partial L}{\\partial \\boldsymbol\\phi} = \\begin{bmatrix}\\frac{\\partial L}{\\partial \\phi_0} \\\\\\frac{\\partial L}{\\partial \\phi_1} \\end{bmatrix}.\n",
         "\\end{equation}"
-      ],
+      ]
-      "metadata": {
-        "id": "s9Duf05WqqSC"
-      }
     },
     {
       "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "UpswmkL2qwBT"
+      },
+      "outputs": [],
       "source": [
         "# These came from writing out the expression for the sum of squares loss and taking the\n",
         "# derivative with respect to phi0 and phi1. It was a lot of hassle to get it right!\n",
@@ -281,31 +276,32 @@
         "    dl_dphi1 = gabor_deriv_phi1(data_x, data_y, phi[0],phi[1])\n",
         "    # Return the gradient\n",
         "    return np.array([[dl_dphi0],[dl_dphi1]])"
-      ],
+      ]
-      "metadata": {
-        "id": "UpswmkL2qwBT"
-      },
-      "execution_count": null,
-      "outputs": []
     },
     {
+      "attachments": {},
       "cell_type": "markdown",
+      "metadata": {
+        "id": "RS1nEcYVuEAM"
+      },
       "source": [
         "We can check we got this right using a trick known as **finite differences**.  If we evaluate the function and then change one of the parameters by a very small amount and normalize by that amount, we get an approximation to the gradient, so:\n",
         "\n",
-        "\\begin{eqnarray}\n",
+        "\\begin{align}\n",
         "\\frac{\\partial L}{\\partial \\phi_{0}}&\\approx & \\frac{L[\\phi_0+\\delta, \\phi_1]-L[\\phi_0, \\phi_1]}{\\delta}\\\\\n",
         "\\frac{\\partial L}{\\partial \\phi_{1}}&\\approx & \\frac{L[\\phi_0, \\phi_1+\\delta]-L[\\phi_0, \\phi_1]}{\\delta}\n",
-        "\\end{eqnarray}\n",
+        "\\end{align}\n",
         "\n",
         "We can't do this when there are many parameters;  for a million parameters, we would have to evaluate the loss function two million times, and usually computing the gradients directly is much more efficient."
-      ],
+      ]
-      "metadata": {
-        "id": "RS1nEcYVuEAM"
-      }
     },
     {
       "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "QuwAHN7yt-gi"
+      },
+      "outputs": [],
       "source": [
         "# Compute the gradient using your function\n",
         "gradient = compute_gradient(data[0,:],data[1,:], phi)\n",
@@ -317,24 +313,25 @@
         "dl_dphi1_est = (compute_loss(data[0,:],data[1,:],model,phi+np.array([[0],[delta]])) - \\\n",
         "                    compute_loss(data[0,:],data[1,:],model,phi))/delta\n",
         "print(\"Approx gradients: (%3.3f,%3.3f)\"%(dl_dphi0_est,dl_dphi1_est))\n"
-      ],
+      ]
-      "metadata": {
-        "id": "QuwAHN7yt-gi"
-      },
-      "execution_count": null,
-      "outputs": []
     },
     {
+      "attachments": {},
       "cell_type": "markdown",
-      "source": [
-        "Now we are ready to perform gradient descent.  We'll need to use our line search routine from Notebook 6.1, which I've reproduced here plus the helper function loss_function_1D that converts from a 2D problem to a 1D problem"
-      ],
       "metadata": {
         "id": "5EIjMM9Fw2eT"
-      }
+      },
+      "source": [
+        "Now we are ready to perform gradient descent.  We'll need to use our line search routine from Notebook 6.1, which I've reproduced here plus the helper function loss_function_1D that converts from a 2D problem to a 1D problem"
+      ]
     },
     {
       "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "XrJ2gQjfw1XP"
+      },
+      "outputs": [],
       "source": [
         "def loss_function_1D(dist_prop, data, model, phi_start, gradient):\n",
         "  # Return the loss after moving this far\n",
@@ -389,15 +386,15 @@
         "\n",
         "    # Return average of two middle points\n",
         "    return (b+c)/2.0"
-      ],
+      ]
-      "metadata": {
-        "id": "XrJ2gQjfw1XP"
-      },
-      "execution_count": null,
-      "outputs": []
     },
     {
       "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "YVq6rmaWRD2M"
+      },
+      "outputs": [],
       "source": [
         "def gradient_descent_step(phi, data,  model):\n",
         "  # Step 1:  Compute the gradient\n",
@@ -406,15 +403,15 @@
         "  alpha = line_search(data, model, phi, gradient*-1, max_dist = 2.0)\n",
         "  phi = phi - alpha * gradient\n",
         "  return phi"
-      ],
+      ]
-      "metadata": {
-        "id": "YVq6rmaWRD2M"
-      },
-      "execution_count": null,
-      "outputs": []
     },
     {
       "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "tOLd0gtdRLLS"
+      },
+      "outputs": [],
       "source": [
         "# Initialize the parameters\n",
         "n_steps = 21\n",
@@ -435,41 +432,41 @@
         "    draw_model(data,model,phi_all[:,c_step+1], \"Iteration %d, loss = %f\"%(c_step+1,loss))\n",
         "\n",
         "draw_loss_function(compute_loss, data, model,phi_all)\n"
-      ],
+      ]
-      "metadata": {
-        "id": "tOLd0gtdRLLS"
-      },
-      "execution_count": null,
-      "outputs": []
     },
     {
       "cell_type": "code",
-      "source": [
+      "execution_count": null,
-        "# TODO Experiment with starting the optimization in the previous cell in different places\n",
-        "# and show that it heads to a local minimum if we don't start it in the right valley"
-      ],
       "metadata": {
         "id": "Oi8ZlH0ptLqA"
       },
-      "execution_count": null,
+      "outputs": [],
-      "outputs": []
+      "source": [
+        "# TODO Experiment with starting the optimization in the previous cell in different places\n",
+        "# and show that it heads to a local minimum if we don't start it in the right valley"
+      ]
     },
     {
       "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "4l-ueLk-oAxV"
+      },
+      "outputs": [],
       "source": [
         "def gradient_descent_step_fixed_learning_rate(phi, data, alpha):\n",
         "  # TODO -- fill in this routine so that we take a fixed size step of size alpha without using line search\n",
         "\n",
         "  return phi"
-      ],
+      ]
-      "metadata": {
-        "id": "4l-ueLk-oAxV"
-      },
-      "execution_count": null,
-      "outputs": []
     },
     {
       "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "oi9MX_GRpM41"
+      },
+      "outputs": [],
       "source": [
         "# Initialize the parameters\n",
         "n_steps = 21\n",
@@ -490,47 +487,47 @@
         "    draw_model(data,model,phi_all[:,c_step+1], \"Iteration %d, loss = %f\"%(c_step+1,loss))\n",
         "\n",
         "draw_loss_function(compute_loss, data, model,phi_all)\n"
-      ],
+      ]
-      "metadata": {
-        "id": "oi9MX_GRpM41"
-      },
-      "execution_count": null,
-      "outputs": []
     },
     {
       "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "In6sQ5YCpMqn"
+      },
+      "outputs": [],
       "source": [
         "# TODO Experiment with the learning rate, alpha.\n",
         "# What happens if you set it too large?\n",
         "# What happens if you set it too small?"
-      ],
+      ]
-      "metadata": {
-        "id": "In6sQ5YCpMqn"
-      },
-      "execution_count": null,
-      "outputs": []
     },
     {
       "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "VKTC9-1Gpm3N"
+      },
+      "outputs": [],
       "source": [
         "def stochastic_gradient_descent_step(phi, data, alpha, batch_size):\n",
         "  # TODO -- fill in this routine so that we take a fixed size step of size alpha but only using a subset (batch) of the data\n",
         "  # at each step\n",
         "  # You can use the function np.random.permutation to generate a random permutation of the n_data = data.shape[1] indices\n",
         "  # and then just choose the first n=batch_size of these indices.  Then compute the gradient update\n",
-        "  # from just the data with these indices.   More properly, you should sample with replacement, but this will do for now.\n",
+        "  # from just the data with these indices.   More properly, you should sample without replacement, but this will do for now.\n",
         "\n",
         "\n",
         "  return phi"
-      ],
+      ]
-      "metadata": {
-        "id": "VKTC9-1Gpm3N"
-      },
-      "execution_count": null,
-      "outputs": []
     },
     {
       "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "469OP_UHskJ4"
+      },
+      "outputs": [],
       "source": [
         "# Set the random number generator so you always get same numbers (disable if you don't want this)\n",
         "np.random.seed(1)\n",
@@ -553,34 +550,45 @@
         "    draw_model(data,model,phi_all[:,c_step+1], \"Iteration %d, loss = %f\"%(c_step+1,loss))\n",
         "\n",
         "draw_loss_function(compute_loss, data, model,phi_all)"
-      ],
+      ]
-      "metadata": {
-        "id": "469OP_UHskJ4"
-      },
-      "execution_count": null,
-      "outputs": []
     },
     {
       "cell_type": "code",
-      "source": [
+      "execution_count": null,
-        "# TODO -- Experiment with different learning rates, starting points, batch sizes, number of steps.  Get a feel for this."
-      ],
       "metadata": {
         "id": "LxE2kTa3s29p"
       },
-      "execution_count": null,
+      "outputs": [],
-      "outputs": []
+      "source": [
+        "# TODO -- Experiment with different learning rates, starting points, batch sizes, number of steps.  Get a feel for this."
+      ]
     },
     {
       "cell_type": "code",
-      "source": [
+      "execution_count": null,
-        "# TODO -- Add a learning rate schedule.  Reduce the learning rate by a factor of beta every M iterations"
-      ],
       "metadata": {
         "id": "lw4QPOaQTh5e"
       },
-      "execution_count": null,
+      "outputs": [],
-      "outputs": []
+      "source": [
+        "# TODO -- Add a learning rate schedule.  Reduce the learning rate by a factor of beta every M iterations"
+      ]
     }
-  ]
+  ],
-}
+  "metadata": {
+    "colab": {
+      "authorship_tag": "ABX9TyNk5FN4qlw3pk8BwDVWw1jN",
+      "include_colab_link": true,
+      "provenance": []
+    },
+    "kernelspec": {
+      "display_name": "Python 3",
+      "name": "python3"
+    },
+    "language_info": {
+      "name": "python"
+    }
+  },
+  "nbformat": 4,
+  "nbformat_minor": 0
+}

Notebooks/Chap06/6_4_Momentum.ipynb

@@ -4,7 +4,6 @@
   "metadata": {
     "colab": {
       "provenance": [],
-      "authorship_tag": "ABX9TyMLS4qeqBTVHGdg9Sds9jND",
       "include_colab_link": true
     },
     "kernelspec": {
@@ -123,7 +122,7 @@
     {
       "cell_type": "code",
       "source": [
-        "# Initialize the parmaeters and draw the model\n",
+        "# Initialize the parameters and draw the model\n",
         "phi = np.zeros((2,1))\n",
         "phi[0] =  -5     # Horizontal offset\n",
         "phi[1] =  25     # Frequency\n",
@@ -377,6 +376,15 @@
       },
       "execution_count": null,
       "outputs": []
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "Note that for this case, Nesterov momentum does not improve the result."
+      ],
+      "metadata": {
+        "id": "F-As4hS8s2nm"
+      }
     }
   ]
 }

Notebooks/Chap06/6_5_Adam.ipynb

@@ -248,7 +248,7 @@
         "        # Replace this line:\n",
         "        v = v\n",
         "\n",
-        "        # TODO -- Modify the statistics according to euation 6.16\n",
+        "        # TODO -- Modify the statistics according to equation 6.16\n",
         "        # You will need the function np.power\n",
         "        # Replace these lines\n",
         "        m_tilde = m\n",

Notebooks/Chap07/7_1_Backpropagation_in_Toy_Model.ipynb

@@ -1,33 +1,22 @@
 {
-  "nbformat": 4,
-  "nbformat_minor": 0,
-  "metadata": {
-    "colab": {
-      "provenance": [],
-      "authorship_tag": "ABX9TyP5wHK5E7/el+vxU947K3q8",
-      "include_colab_link": true
-    },
-    "kernelspec": {
-      "name": "python3",
-      "display_name": "Python 3"
-    },
-    "language_info": {
-      "name": "python"
-    }
-  },
   "cells": [
     {
+      "attachments": {},
       "cell_type": "markdown",
       "metadata": {
-        "id": "view-in-github",
+        "colab_type": "text",
-        "colab_type": "text"
+        "id": "view-in-github"
       },
       "source": [
         "<a href=\"https://colab.research.google.com/github/udlbook/udlbook/blob/main/Notebooks/Chap07/7_1_Backpropagation_in_Toy_Model.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
       ]
     },
     {
+      "attachments": {},
       "cell_type": "markdown",
+      "metadata": {
+        "id": "pOZ6Djz0dhoy"
+      },
       "source": [
         "# **Notebook 7.1: Backpropagation in Toy Model**\n",
         "\n",
@@ -36,64 +25,63 @@
         "Work through the cells below, running each cell in turn. In various places you will see the words \"TO DO\". Follow the instructions at these places and make predictions about what is going to happen or write code to complete the functions.\n",
         "\n",
         "Contact me at udlbookmail@gmail.com if you find any mistakes or have any suggestions."
-      ],
+      ]
-      "metadata": {
-        "id": "pOZ6Djz0dhoy"
-      }
     },
     {
+      "attachments": {},
       "cell_type": "markdown",
+      "metadata": {
+        "id": "1DmMo2w63CmT"
+      },
       "source": [
         "We're going to investigate how to take the derivatives of functions where one operation is composed with another, which is composed with a third and so on.  For example, consider the model:\n",
         "\n",
         "\\begin{equation}\n",
-        "     \\mbox{f}[x,\\boldsymbol\\phi] = \\beta_3+\\omega_3\\cdot\\cos\\Bigl[\\beta_2+\\omega_2\\cdot\\exp\\bigl[\\beta_1+\\omega_1\\cdot\\sin[\\beta_0+\\omega_0x]\\bigr]\\Bigr],\n",
+        "     \\text{f}[x,\\boldsymbol\\phi] = \\beta_3+\\omega_3\\cdot\\cos\\Bigl[\\beta_2+\\omega_2\\cdot\\exp\\bigl[\\beta_1+\\omega_1\\cdot\\sin[\\beta_0+\\omega_0x]\\bigr]\\Bigr],\n",
         "\\end{equation}\n",
         "\n",
         "with parameters $\\boldsymbol\\phi=\\{\\beta_0,\\omega_0,\\beta_1,\\omega_1,\\beta_2,\\omega_2,\\beta_3,\\omega_3\\}$.<br>\n",
         "\n",
         "This is a composition of the functions $\\cos[\\bullet],\\exp[\\bullet],\\sin[\\bullet]$.   I chose these just because you probably already know the derivatives of these functions:\n",
         "\n",
-        "\\begin{eqnarray*}\n",
+        "\\begin{align}\n",
         " \\frac{\\partial \\cos[z]}{\\partial z} = -\\sin[z] \\quad\\quad \\frac{\\partial \\exp[z]}{\\partial z} = \\exp[z] \\quad\\quad \\frac{\\partial \\sin[z]}{\\partial z} = \\cos[z].\n",
-        "\\end{eqnarray*}\n",
+        "\\end{align}\n",
         "\n",
         "Suppose that we have a least squares loss function:\n",
         "\n",
         "\\begin{equation*}\n",
-        "\\ell_i = (\\mbox{f}[x_i,\\boldsymbol\\phi]-y_i)^2,\n",
+        "\\ell_i = (\\text{f}[x_i,\\boldsymbol\\phi]-y_i)^2,\n",
         "\\end{equation*}\n",
         "\n",
         "Assume that we know the current values of $\\beta_{0},\\beta_{1},\\beta_{2},\\beta_{3},\\omega_{0},\\omega_{1},\\omega_{2},\\omega_{3}$, $x_i$ and $y_i$. We could obviously calculate $\\ell_i$.   But we also want to know how $\\ell_i$ changes when we make a small change to $\\beta_{0},\\beta_{1},\\beta_{2},\\beta_{3},\\omega_{0},\\omega_{1},\\omega_{2}$, or $\\omega_{3}$.  In other words, we want to compute the eight derivatives:\n",
         "\n",
-        "\\begin{eqnarray*}\n",
+        "\\begin{align}\n",
-        "\\frac{\\partial \\ell_i}{\\partial \\beta_{0}}, \\quad \\frac{\\partial \\ell_i}{\\partial \\beta_{1}}, \\quad \\frac{\\partial \\ell_i}{\\partial \\beta_{2}}, \\quad \\frac{\\partial \\ell_i }{\\partial \\beta_{3}},  \\quad \\frac{\\partial \\ell_i}{\\partial \\omega_{0}}, \\quad \\frac{\\partial \\ell_i}{\\partial \\omega_{1}}, \\quad \\frac{\\partial \\ell_i}{\\partial \\omega_{2}},  \\quad\\mbox{and} \\quad \\frac{\\partial \\ell_i}{\\partial \\omega_{3}}.\n",
+        "\\frac{\\partial \\ell_i}{\\partial \\beta_{0}}, \\quad \\frac{\\partial \\ell_i}{\\partial \\beta_{1}}, \\quad \\frac{\\partial \\ell_i}{\\partial \\beta_{2}}, \\quad \\frac{\\partial \\ell_i }{\\partial \\beta_{3}},  \\quad \\frac{\\partial \\ell_i}{\\partial \\omega_{0}}, \\quad \\frac{\\partial \\ell_i}{\\partial \\omega_{1}}, \\quad \\frac{\\partial \\ell_i}{\\partial \\omega_{2}},  \\quad\\text{and} \\quad \\frac{\\partial \\ell_i}{\\partial \\omega_{3}}.\n",
-        "\\end{eqnarray*}"
+        "\\end{align}"
-      ],
+      ]
-      "metadata": {
-        "id": "1DmMo2w63CmT"
-      }
     },
     {
       "cell_type": "code",
-      "source": [
+      "execution_count": null,
-        "# import library\n",
-        "import numpy as np"
-      ],
       "metadata": {
         "id": "RIPaoVN834Lj"
       },
-      "execution_count": null,
+      "outputs": [],
-      "outputs": []
+      "source": [
+        "# import library\n",
+        "import numpy as np"
+      ]
     },
     {
+      "attachments": {},
       "cell_type": "markdown",
-      "source": [
-        "Let's first define the original function for $y$ and the likelihood term:"
-      ],
       "metadata": {
         "id": "32-ufWhc3v2c"
-      }
+      },
+      "source": [
+        "Let's first define the original function for $y$ and the loss term:"
+      ]
     },
     {
       "cell_type": "code",
@@ -106,103 +94,135 @@
         "def fn(x, beta0, beta1, beta2, beta3, omega0, omega1, omega2, omega3):\n",
         "  return beta3+omega3 * np.cos(beta2 + omega2 * np.exp(beta1 + omega1 * np.sin(beta0 + omega0 * x)))\n",
         "\n",
-        "def likelihood(x, y, beta0, beta1, beta2, beta3, omega0, omega1, omega2, omega3):\n",
+        "def loss(x, y, beta0, beta1, beta2, beta3, omega0, omega1, omega2, omega3):\n",
         "  diff = fn(x, beta0, beta1, beta2, beta3, omega0, omega1, omega2, omega3) - y\n",
         "  return diff * diff"
       ]
     },
     {
+      "attachments": {},
       "cell_type": "markdown",
-      "source": [
-        "Now we'll choose some values for the betas and the omegas and x and compute the output of the function:"
-      ],
       "metadata": {
         "id": "y7tf0ZMt5OXt"
-      }
+      },
+      "source": [
+        "Now we'll choose some values for the betas and the omegas and x and compute the output of the function:"
+      ]
     },
     {
       "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "pwvOcCxr41X_",
+        "outputId": "9541922c-dfc4-4b2e-dfa3-3298812155ce"
+      },
+      "outputs": [
+        {
+          "name": "stdout",
+          "output_type": "stream",
+          "text": [
+            "l_i=0.139\n"
+          ]
+        }
+      ],
       "source": [
         "beta0 = 1.0; beta1 = 2.0; beta2 = -3.0; beta3 = 0.4\n",
         "omega0 = 0.1; omega1 = -0.4; omega2 = 2.0; omega3 = 3.0\n",
         "x = 2.3; y =2.0\n",
-        "l_i_func = likelihood(x,y,beta0,beta1,beta2,beta3,omega0,omega1,omega2,omega3)\n",
+        "l_i_func = loss(x,y,beta0,beta1,beta2,beta3,omega0,omega1,omega2,omega3)\n",
         "print('l_i=%3.3f'%l_i_func)"
-      ],
+      ]
-      "metadata": {
-        "id": "pwvOcCxr41X_"
-      },
-      "execution_count": null,
-      "outputs": []
     },
     {
+      "attachments": {},
       "cell_type": "markdown",
+      "metadata": {
+        "id": "u5w69NeT64yV"
+      },
       "source": [
         "# Computing derivatives by hand\n",
         "\n",
         "We could compute expressions for the derivatives by hand and write code to compute them directly but some have very complex expressions, even for this relatively simple original equation. For example:\n",
         "\n",
-        "\\begin{eqnarray*}\n",
+        "\\begin{align}\n",
         "\\frac{\\partial \\ell_i}{\\partial \\omega_{0}} &=& -2 \\left( \\beta_3+\\omega_3\\cdot\\cos\\Bigl[\\beta_2+\\omega_2\\cdot\\exp\\bigl[\\beta_1+\\omega_1\\cdot\\sin[\\beta_0+\\omega_0\\cdot x_i]\\bigr]\\Bigr]-y_i\\right)\\nonumber \\\\\n",
         "&&\\hspace{0.5cm}\\cdot \\omega_1\\omega_2\\omega_3\\cdot x_i\\cdot\\cos[\\beta_0+\\omega_0 \\cdot x_i]\\cdot\\exp\\Bigl[\\beta_1 + \\omega_1 \\cdot \\sin[\\beta_0+\\omega_0\\cdot x_i]\\Bigr]\\nonumber\\\\\n",
         "&& \\hspace{1cm}\\cdot \\sin\\biggl[\\beta_2+\\omega_2\\cdot \\exp\\Bigl[\\beta_1 + \\omega_1 \\cdot \\sin[\\beta_0+\\omega_0\\cdot x_i]\\Bigr]\\biggr].\n",
-        "\\end{eqnarray*}"
+        "\\end{align}"
-      ],
+      ]
-      "metadata": {
-        "id": "u5w69NeT64yV"
-      }
     },
     {
       "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "7t22hALp5zkq"
+      },
+      "outputs": [],
       "source": [
         "dldbeta3_func = 2 * (beta3 +omega3 * np.cos(beta2 + omega2 * np.exp(beta1+omega1 * np.sin(beta0+omega0 * x)))-y)\n",
         "dldomega0_func = -2 *(beta3 +omega3 * np.cos(beta2 + omega2 * np.exp(beta1+omega1 * np.sin(beta0+omega0 * x)))-y) * \\\n",
         "              omega1 * omega2 * omega3 * x * np.cos(beta0 + omega0 * x) * np.exp(beta1 +omega1 * np.sin(beta0 + omega0 * x)) *\\\n",
         "              np.sin(beta2 + omega2 * np.exp(beta1+ omega1* np.sin(beta0+omega0 * x)))"
-      ],
+      ]
-      "metadata": {
-        "id": "7t22hALp5zkq"
-      },
-      "execution_count": null,
-      "outputs": []
     },
     {
+      "attachments": {},
       "cell_type": "markdown",
-      "source": [
-        "Let's make sure this is correct using finite differences:"
-      ],
       "metadata": {
         "id": "iRh4hnu3-H3n"
-      }
+      },
+      "source": [
+        "Let's make sure this is correct using finite differences:"
+      ]
     },
     {
       "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "1O3XmXMx-HlZ",
+        "outputId": "389ed78e-9d8d-4e8b-9e6b-5f20c21407e8"
+      },
+      "outputs": [
+        {
+          "name": "stdout",
+          "output_type": "stream",
+          "text": [
+            "dydomega0: Function value = 5.246, Finite difference value = 5.246\n"
+          ]
+        }
+      ],
       "source": [
-        "dldomega0_fd = (likelihood(x,y,beta0,beta1,beta2,beta3,omega0+0.00001,omega1,omega2,omega3)-likelihood(x,y,beta0,beta1,beta2,beta3,omega0,omega1,omega2,omega3))/0.00001\n",
+        "dldomega0_fd = (loss(x,y,beta0,beta1,beta2,beta3,omega0+0.00001,omega1,omega2,omega3)-loss(x,y,beta0,beta1,beta2,beta3,omega0,omega1,omega2,omega3))/0.00001\n",
         "\n",
         "print('dydomega0: Function value = %3.3f, Finite difference value = %3.3f'%(dldomega0_func,dldomega0_fd))"
-      ],
+      ]
-      "metadata": {
-        "id": "1O3XmXMx-HlZ"
-      },
-      "execution_count": null,
-      "outputs": []
     },
     {
+      "attachments": {},
       "cell_type": "markdown",
-      "source": [
-        "The code to calculate $\\partial l_i/ \\partial \\omega_0$ is a bit of a nightmare.  It's easy to make mistakes, and you can see that some parts of it are repeated (for example, the $\\sin[\\bullet]$ term), which suggests some kind of redundancy in the calculations.  The goal of this practical is to compute the derivatives in a much simpler way.  There will be three steps:"
-      ],
       "metadata": {
         "id": "wS4IPjZAKWTN"
-      }
+      },
+      "source": [
+        "The code to calculate $\\partial l_i/ \\partial \\omega_0$ is a bit of a nightmare.  It's easy to make mistakes, and you can see that some parts of it are repeated (for example, the $\\sin[\\bullet]$ term), which suggests some kind of redundancy in the calculations.  The goal of this practical is to compute the derivatives in a much simpler way.  There will be three steps:"
+      ]
     },
     {
+      "attachments": {},
       "cell_type": "markdown",
+      "metadata": {
+        "id": "8UWhvDeNDudz"
+      },
       "source": [
         "**Step 1:** Write the original equations as a series of intermediate calculations.\n",
         "\n",
-        "\\begin{eqnarray}\n",
+        "\\begin{align}\n",
         "f_{0} &=& \\beta_{0} + \\omega_{0} x_i\\nonumber\\\\\n",
         "h_{1} &=& \\sin[f_{0}]\\nonumber\\\\\n",
         "f_{1} &=& \\beta_{1} + \\omega_{1}h_{1}\\nonumber\\\\\n",
@@ -211,16 +231,18 @@
         "h_{3} &=& \\cos[f_{2}]\\nonumber\\\\\n",
         "f_{3} &=& \\beta_{3} + \\omega_{3}h_{3}\\nonumber\\\\\n",
         "l_i &=& (f_3-y_i)^2\n",
-        "\\end{eqnarray}\n",
+        "\\end{align}\n",
         "\n",
         "and compute and store the values of all of these intermediate values.  We'll need them to compute the derivatives.<br>  This is called the **forward pass**."
-      ],
+      ]
-      "metadata": {
-        "id": "8UWhvDeNDudz"
-      }
     },
     {
       "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "ZWKAq6HC90qV"
+      },
+      "outputs": [],
       "source": [
         "# TODO compute all the f_k and h_k terms\n",
         "# Replace the code below\n",
@@ -233,15 +255,34 @@
         "h3 = 0\n",
         "f3 = 0\n",
         "l_i = 0\n"
-      ],
+      ]
-      "metadata": {
-        "id": "ZWKAq6HC90qV"
-      },
-      "execution_count": null,
-      "outputs": []
     },
     {
       "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "ibxXw7TUW4Sx",
+        "outputId": "4575e3eb-2b16-4e0b-c84e-9c22b443c3ce"
+      },
+      "outputs": [
+        {
+          "name": "stdout",
+          "output_type": "stream",
+          "text": [
+            "f0: true value = 1.230, your value = 0.000\n",
+            "h1: true value = 0.942, your value = 0.000\n",
+            "f1: true value = 1.623, your value = 0.000\n",
+            "h2: true value = 5.068, your value = 0.000\n",
+            "f2: true value = 7.137, your value = 0.000\n",
+            "h3: true value = 0.657, your value = 0.000\n",
+            "f3: true value = 2.372, your value = 0.000\n",
+            "like original = 0.139, like from forward pass = 0.000\n"
+          ]
+        }
+      ],
       "source": [
         "# Let's check we got that right:\n",
         "print(\"f0: true value = %3.3f, your value = %3.3f\"%(1.230, f0))\n",
@@ -252,22 +293,21 @@
         "print(\"h3: true value = %3.3f, your value = %3.3f\"%(0.657, h3))\n",
         "print(\"f3: true value = %3.3f, your value = %3.3f\"%(2.372, f3))\n",
         "print(\"like original = %3.3f, like from forward pass = %3.3f\"%(l_i_func, l_i))\n"
-      ],
+      ]
-      "metadata": {
-        "id": "ibxXw7TUW4Sx"
-      },
-      "execution_count": null,
-      "outputs": []
     },
     {
+      "attachments": {},
       "cell_type": "markdown",
+      "metadata": {
+        "id": "jay8NYWdFHuZ"
+      },
       "source": [
-        "**Step 2:** Compute the derivatives of $y$ with respect to the intermediate quantities that we just calculated, but in reverse order:\n",
+        "**Step 2:** Compute the derivatives of $\\ell_i$ with respect to the intermediate quantities that we just calculated, but in reverse order:\n",
         "\n",
-        "\\begin{eqnarray}\n",
+        "\\begin{align}\n",
         "\\quad \\frac{\\partial \\ell_i}{\\partial f_3}, \\quad \\frac{\\partial \\ell_i}{\\partial h_3}, \\quad \\frac{\\partial \\ell_i}{\\partial f_2}, \\quad\n",
-        "\\frac{\\partial \\ell_i}{\\partial h_2}, \\quad \\frac{\\partial \\ell_i}{\\partial f_1}, \\quad \\frac{\\partial \\ell_i}{\\partial h_1},  \\quad\\mbox{and} \\quad \\frac{\\partial \\ell_i}{\\partial f_0}.\n",
+        "\\frac{\\partial \\ell_i}{\\partial h_2}, \\quad \\frac{\\partial \\ell_i}{\\partial f_1}, \\quad \\frac{\\partial \\ell_i}{\\partial h_1},  \\quad\\text{and} \\quad \\frac{\\partial \\ell_i}{\\partial f_0}.\n",
-        "\\end{eqnarray}\n",
+        "\\end{align}\n",
         "\n",
         "The first of these derivatives is straightforward:\n",
         "\n",
@@ -281,11 +321,11 @@
         "\\frac{\\partial \\ell_i}{\\partial h_{3}} =\\frac{\\partial f_{3}}{\\partial h_{3}} \\frac{\\partial \\ell_i}{\\partial f_{3}} .\n",
         "\\end{equation}\n",
         "\n",
-        "The left-hand side asks how $\\ell_i$ changes when $h_{3}$ changes.  The right-hand side says we can decompose this into (i) how $ell_i$ changes when $f_{3}$ changes and how $f_{3}$ changes when $h_{3}$ changes.  So you get a chain of events happening:  $h_{3}$ changes $f_{3}$, which changes $\\ell_i$, and the derivatives represent the effects of this chain.  Notice that we computed the first of these derivatives already and is  $2 (f_3-y)$. We calculated $f_{3}$ in step 1.  The second term is the derivative of $\\beta_{3} + \\omega_{3}h_{3}$ with respect to $h_3$ which is simply $\\omega_3$.  \n",
+        "The left-hand side asks how $\\ell_i$ changes when $h_{3}$ changes.  The right-hand side says we can decompose this into (i) how $\\ell_i$ changes when $f_{3}$ changes and how $f_{3}$ changes when $h_{3}$ changes.  So you get a chain of events happening:  $h_{3}$ changes $f_{3}$, which changes $\\ell_i$, and the derivatives represent the effects of this chain.  Notice that we computed the first of these derivatives already and is  $2 (f_3-y)$. We calculated $f_{3}$ in step 1.  The second term is the derivative of $\\beta_{3} + \\omega_{3}h_{3}$ with respect to $h_3$ which is simply $\\omega_3$.  \n",
         "\n",
         "We can continue in this way, computing the derivatives of the output with respect to these intermediate quantities:\n",
         "\n",
-        "\\begin{eqnarray}\n",
+        "\\begin{align}\n",
         "\\frac{\\partial \\ell_i}{\\partial f_{2}} &=& \\frac{\\partial h_{3}}{\\partial f_{2}}\\left(\n",
         "\\frac{\\partial f_{3}}{\\partial h_{3}}\\frac{\\partial \\ell_i}{\\partial f_{3}} \\right)\n",
         "\\nonumber \\\\\n",
@@ -293,16 +333,18 @@
         "\\frac{\\partial \\ell_i}{\\partial f_{1}} &=& \\frac{\\partial h_{2}}{\\partial f_{1}}\\left( \\frac{\\partial f_{2}}{\\partial h_{2}}\\frac{\\partial h_{3}}{\\partial f_{2}}\\frac{\\partial f_{3}}{\\partial h_{3}}\\frac{\\partial \\ell_i}{\\partial f_{3}} \\right)\\nonumber \\\\\n",
         "\\frac{\\partial \\ell_i}{\\partial h_{1}} &=& \\frac{\\partial f_{1}}{\\partial h_{1}}\\left(\\frac{\\partial h_{2}}{\\partial f_{1}} \\frac{\\partial f_{2}}{\\partial h_{2}}\\frac{\\partial h_{3}}{\\partial f_{2}}\\frac{\\partial f_{3}}{\\partial h_{3}}\\frac{\\partial \\ell_i}{\\partial f_{3}} \\right)\\nonumber \\\\\n",
         "\\frac{\\partial \\ell_i}{\\partial f_{0}} &=& \\frac{\\partial h_{1}}{\\partial f_{0}}\\left(\\frac{\\partial f_{1}}{\\partial h_{1}}\\frac{\\partial h_{2}}{\\partial f_{1}} \\frac{\\partial f_{2}}{\\partial h_{2}}\\frac{\\partial h_{3}}{\\partial f_{2}}\\frac{\\partial f_{3}}{\\partial h_{3}}\\frac{\\partial \\ell_i}{\\partial f_{3}} \\right).\n",
-        "\\end{eqnarray}\n",
+        "\\end{align}\n",
         "\n",
         "In each case, we have already computed all of the terms except the last one in the previous step, and the last term is simple to evaluate.  This is called the **backward pass**."
-      ],
+      ]
-      "metadata": {
-        "id": "jay8NYWdFHuZ"
-      }
     },
     {
       "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "gCQJeI--Egdl"
+      },
+      "outputs": [],
       "source": [
         "# TODO -- Compute the derivatives of the output with respect\n",
         "# to the intermediate computations h_k and f_k (i.e, run the backward pass)\n",
@@ -315,15 +357,33 @@
         "dldf1 = 1\n",
         "dldh1 = 1\n",
         "dldf0 = 1\n"
-      ],
+      ]
-      "metadata": {
-        "id": "gCQJeI--Egdl"
-      },
-      "execution_count": null,
-      "outputs": []
     },
     {
       "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "dS1OrLtlaFr7",
+        "outputId": "414f0862-ae36-4a0e-b68f-4758835b0e23"
+      },
+      "outputs": [
+        {
+          "name": "stdout",
+          "output_type": "stream",
+          "text": [
+            "dldf3: true value = 0.745, your value = -4.000\n",
+            "dldh3: true value = 2.234, your value = -12.000\n",
+            "dldf2: true value = -1.683, your value = 1.000\n",
+            "dldh2: true value = -3.366, your value = 1.000\n",
+            "dldf1: true value = -17.060, your value = 1.000\n",
+            "dldh1: true value = 6.824, your value = 1.000\n",
+            "dldf0: true value = 2.281, your value = 1.000\n"
+          ]
+        }
+      ],
       "source": [
         "# Let's check we got that right\n",
         "print(\"dldf3: true value = %3.3f, your value = %3.3f\"%(0.745, dldf3))\n",
@@ -333,38 +393,15 @@
         "print(\"dldf1: true value = %3.3f, your value = %3.3f\"%(-17.060, dldf1))\n",
         "print(\"dldh1: true value = %3.3f, your value = %3.3f\"%(6.824, dldh1))\n",
         "print(\"dldf0: true value = %3.3f, your value = %3.3f\"%(2.281, dldf0))"
-      ],
+      ]
-      "metadata": {
-        "id": "dS1OrLtlaFr7"
-      },
-      "execution_count": null,
-      "outputs": []
-    },
-    {
-      "cell_type": "markdown",
-      "source": [
-        "**Step 3:**  Finally, we consider how the loss~$\\ell_{i}$ changes when we change the parameters $\\beta_{\\bullet}$ and $\\omega_{\\bullet}$. Once more, we apply the chain rule:\n",
-        "\n",
-        "\n",
-        "\n",
-        "\n",
-        "\\begin{eqnarray}\n",
-        "\\frac{\\partial \\ell_i}{\\partial \\beta_{k}} &=& \\frac{\\partial f_{k}}{\\partial \\beta_{k}}\\frac{\\partial \\ell_i}{\\partial f_{k}}\\nonumber \\\\\n",
-        "\\frac{\\partial \\ell_i}{\\partial \\omega_{k}} &=& \\frac{\\partial f_{k}}{\\partial \\omega_{k}}\\frac{\\partial \\ell_i}{\\partial f_{k}}.\n",
-        "\\end{eqnarray}\n",
-        "\n",
-        "\\noindent In each case, the second term on the right-hand side was computed in step 2. When $k>0$, we have~$f_{k}=\\beta_{k}+\\omega_k \\cdot h_{k}$, so:\n",
-        "\n",
-        "\\begin{eqnarray}\n",
-        "\\frac{\\partial f_{k}}{\\partial \\beta_{k}} = 1 \\quad\\quad\\mbox{and}\\quad \\quad \\frac{\\partial f_{k}}{\\partial \\omega_{k}} &=& h_{k}.\n",
-        "\\end{eqnarray}"
-      ],
-      "metadata": {
-        "id": "FlzlThQPGpkU"
-      }
     },
     {
       "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "1I2BhqZhGMK6"
+      },
+      "outputs": [],
       "source": [
         "# TODO -- Calculate the final derivatives with respect to the beta and omega terms\n",
         "\n",
@@ -376,15 +413,34 @@
         "dldomega1 = 1\n",
         "dldbeta0 = 1\n",
         "dldomega0 = 1\n"
-      ],
+      ]
-      "metadata": {
-        "id": "1I2BhqZhGMK6"
-      },
-      "execution_count": null,
-      "outputs": []
     },
     {
       "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "38eiOn2aHgHI",
+        "outputId": "1a67a636-e832-471e-e771-54824363158a"
+      },
+      "outputs": [
+        {
+          "name": "stdout",
+          "output_type": "stream",
+          "text": [
+            "dldbeta3: Your value = 1.000, True value = 0.745\n",
+            "dldomega3: Your value = 1.000, True value = 0.489\n",
+            "dldbeta2: Your value = 1.000, True value = -1.683\n",
+            "dldomega2: Your value = 1.000, True value = -8.530\n",
+            "dldbeta1: Your value = 1.000, True value = -17.060\n",
+            "dldomega1: Your value = 1.000, True value = -16.079\n",
+            "dldbeta0: Your value = 1.000, True value = 2.281\n",
+            "dldomega0: Your value = 1.000, Function value = 5.246, Finite difference value = 5.246\n"
+          ]
+        }
+      ],
       "source": [
         "# Let's check we got them right\n",
         "print('dldbeta3: Your value = %3.3f, True value = %3.3f'%(dldbeta3, 0.745))\n",
@@ -395,21 +451,33 @@
         "print('dldomega1: Your value = %3.3f, True value = %3.3f'%(dldomega1, -16.079))\n",
         "print('dldbeta0: Your value = %3.3f, True value = %3.3f'%(dldbeta0, 2.281))\n",
         "print('dldomega0: Your value = %3.3f, Function value = %3.3f, Finite difference value = %3.3f'%(dldomega0, dldomega0_func, dldomega0_fd))"
-      ],
+      ]
-      "metadata": {
-        "id": "38eiOn2aHgHI"
-      },
-      "execution_count": null,
-      "outputs": []
     },
     {
+      "attachments": {},
       "cell_type": "markdown",
-      "source": [
-        "Using this method, we can compute the derivatives quite easily without needing to compute very complicated expressions.  In the next practical, we'll apply this same method to a deep neural network."
-      ],
       "metadata": {
         "id": "N2ZhrR-2fNa1"
-      }
+      },
+      "source": [
+        "Using this method, we can compute the derivatives quite easily without needing to compute very complicated expressions.  In the next practical, we'll apply this same method to a deep neural network."
+      ]
     }
-  ]
+  ],
-}
+  "metadata": {
+    "colab": {
+      "authorship_tag": "ABX9TyN7JeDgslwtZcwRCOuGuPFt",
+      "include_colab_link": true,
+      "provenance": []
+    },
+    "kernelspec": {
+      "display_name": "Python 3",
+      "name": "python3"
+    },
+    "language_info": {
+      "name": "python"
+    }
+  },
+  "nbformat": 4,
+  "nbformat_minor": 0
+}

Notebooks/Chap07/7_2_Backpropagation.ipynb

@@ -4,7 +4,7 @@
   "metadata": {
     "colab": {
       "provenance": [],
-      "authorship_tag": "ABX9TyN2nPVR0imZntgj4Oasyvmo",
+      "authorship_tag": "ABX9TyM2kkHLr00J4Jeypw41sTkQ",
       "include_colab_link": true
     },
     "kernelspec": {
@@ -244,28 +244,28 @@
         "  all_dl_dh = [None] * (K+1)\n",
         "  # Again for convenience we'll stick with the convention that all_h[0] is the net input and all_f[k] in the net output\n",
         "\n",
-        "  # Compute derivatives of net output with respect to loss\n",
+        "  # Compute derivatives of the loss with respect to the network output\n",
         "  all_dl_df[K] = np.array(d_loss_d_output(all_f[K],y))\n",
         "\n",
         "  # Now work backwards through the network\n",
         "  for layer in range(K,-1,-1):\n",
-        "    # TODO Calculate the derivatives of biases at layer this from all_dl_df[layer]. (eq 7.21)\n",
+        "    # TODO Calculate the derivatives of the loss with respect to the biases at layer this from all_dl_df[layer]. (eq 7.21)\n",
         "    # NOTE!  To take a copy of matrix X, use Z=np.array(X)\n",
         "    # REPLACE THIS LINE\n",
         "    all_dl_dbiases[layer] = np.zeros_like(all_biases[layer])\n",
         "\n",
-        "    # TODO Calculate the derivatives of weight at layer from all_dl_df[K] and all_h[K] (eq 7.22)\n",
+        "    # TODO Calculate the derivatives of the loss with respect to the weights at layer from all_dl_df[layer] and all_h[layer] (eq 7.22)\n",
         "    # Don't forget to use np.matmul\n",
         "    # REPLACE THIS LINE\n",
         "    all_dl_dweights[layer] = np.zeros_like(all_weights[layer])\n",
         "\n",
-        "    # TODO: calculate the derivatives of activations from weight and derivatives of next preactivations (eq 7.20)\n",
+        "    # TODO: calculate the derivatives of the loss with respect to the activations from weight and derivatives of next preactivations (second part of last line of eq 7.24)\n",
         "    # REPLACE THIS LINE\n",
         "    all_dl_dh[layer] = np.zeros_like(all_h[layer])\n",
         "\n",
         "\n",
         "    if layer > 0:\n",
-        "      # TODO Calculate the derivatives of the pre-activation f with respect to activation h (deriv of ReLu function)\n",
+        "      # TODO Calculate the derivatives of the loss with respect to the pre-activation f (use deriv of ReLu function, first part of last line of eq. 7.24)\n",
         "      # REPLACE THIS LINE\n",
         "      all_dl_df[layer-1] = np.zeros_like(all_f[layer-1])\n",
         "\n",
@@ -311,10 +311,16 @@
         "    network_output_2, *_ = compute_network_output(net_input, all_weights, all_biases)\n",
         "    dl_dbias[row] = (least_squares_loss(network_output_1, y) - least_squares_loss(network_output_2,y))/delta_fd\n",
         "  all_dl_dbiases_fd[layer] = np.array(dl_dbias)\n",
+        "  print(\"-----------------------------------------------\")\n",
         "  print(\"Bias %d, derivatives from backprop:\"%(layer))\n",
         "  print(all_dl_dbiases[layer])\n",
         "  print(\"Bias %d, derivatives from finite differences\"%(layer))\n",
         "  print(all_dl_dbiases_fd[layer])\n",
+        "  if np.allclose(all_dl_dbiases_fd[layer],all_dl_dbiases[layer],rtol=1e-05, atol=1e-08, equal_nan=False):\n",
+        "    print(\"Success!  Derivatives match.\")\n",
+        "  else:\n",
+        "    print(\"Failure!  Derivatives different.\")\n",
+        "\n",
         "\n",
         "\n",
         "# Test the derivatives of the weights matrices\n",
@@ -330,10 +336,15 @@
         "      network_output_2, *_ = compute_network_output(net_input, all_weights, all_biases)\n",
         "      dl_dweight[row][col] = (least_squares_loss(network_output_1, y) - least_squares_loss(network_output_2,y))/delta_fd\n",
         "  all_dl_dweights_fd[layer] = np.array(dl_dweight)\n",
+        "  print(\"-----------------------------------------------\")\n",
         "  print(\"Weight %d, derivatives from backprop:\"%(layer))\n",
         "  print(all_dl_dweights[layer])\n",
         "  print(\"Weight %d, derivatives from finite differences\"%(layer))\n",
-        "  print(all_dl_dweights_fd[layer])"
+        "  print(all_dl_dweights_fd[layer])\n",
+        "  if np.allclose(all_dl_dweights_fd[layer],all_dl_dweights[layer],rtol=1e-05, atol=1e-08, equal_nan=False):\n",
+        "    print(\"Success!  Derivatives match.\")\n",
+        "  else:\n",
+        "    print(\"Failure!  Derivatives different.\")"
       ],
       "metadata": {
         "id": "PK-UtE3hreAK"

Notebooks/Chap08/8_1_MNIST_1D_Performance.ipynb

@@ -5,7 +5,7 @@
     "colab": {
       "provenance": [],
       "gpuType": "T4",
-      "authorship_tag": "ABX9TyNLj3HOpVB87nRu7oSLuBaU",
+      "authorship_tag": "ABX9TyOuKMUcKfOIhIL2qTX9jJCy",
       "include_colab_link": true
     },
     "kernelspec": {
@@ -84,7 +84,7 @@
       "cell_type": "code",
       "source": [
         "args = mnist1d.data.get_dataset_args()\n",
-        "data = mnist1d.data.get_dataset(args, path='./mnist1d_data.pkl', download=False, regenerate=False)\n",
+        "data = mnist1d.data.get_dataset(args, path='./sample_data/mnist1d_data.pkl', download=False, regenerate=False)\n",
         "\n",
         "# The training and test input and outputs are in\n",
         "# data['x'], data['y'], data['x_test'], and data['y_test']\n",

Notebooks/Chap08/8_2_Bias_Variance_Trade_Off.ipynb

@@ -4,7 +4,6 @@
   "metadata": {
     "colab": {
       "provenance": [],
-      "authorship_tag": "ABX9TyPz1B8kFc21JvGTDwqniloA",
       "include_colab_link": true
     },
     "kernelspec": {
@@ -77,7 +76,7 @@
         "    for i in range(n_data):\n",
         "        x[i] = np.random.uniform(i/n_data, (i+1)/n_data, 1)\n",
         "\n",
-        "    # y value from running through functoin and adding noise\n",
+        "    # y value from running through function and adding noise\n",
         "    y = np.ones(n_data)\n",
         "    for i in range(n_data):\n",
         "        y[i] = true_function(x[i])\n",
@@ -185,10 +184,8 @@
         "          if A[i,j] < 0:\n",
         "              A[i,j] = 0;\n",
         "\n",
-        "  ATA = np.matmul(np.transpose(A), A)\n",
+        "  beta_omega = np.linalg.lstsq(A, y, rcond=None)[0]\n",
-        "  ATAInv = np.linalg.inv(ATA)\n",
+        "\n",
-        "  ATAInvAT = np.matmul(ATAInv, np.transpose(A))\n",
-        "  beta_omega = np.matmul(ATAInvAT,y)\n",
         "  beta = beta_omega[0]\n",
         "  omega = beta_omega[1:]\n",
         "\n",
@@ -229,7 +226,7 @@
         "  y_model_all = np.zeros((n_datasets, x_model.shape[0]))\n",
         "\n",
         "  for c_dataset in range(n_datasets):\n",
-        "    # TODO -- Generate n_data x,y, pairs with standard divation sigma_func\n",
+        "    # TODO -- Generate n_data x,y, pairs with standard deviation sigma_func\n",
         "    # Replace this line\n",
         "    x_data,y_data = np.zeros([1,n_data]),np.zeros([1,n_data])\n",
         "\n",
@@ -316,7 +313,7 @@
         "\n",
         "  # Compute variance -- average of the model variance (average squared deviation of fitted models around mean fitted model)\n",
         "  variance[c_hidden] = 0\n",
-        "  # Compute bias (average squared deviaton of mean fitted model around true function)\n",
+        "  # Compute bias (average squared deviation of mean fitted model around true function)\n",
         "  bias[c_hidden] = 0\n",
         "\n",
         "# Plot the results\n",

Notebooks/Chap08/8_4_High_Dimensional_Spaces.ipynb

@@ -4,7 +4,7 @@
   "metadata": {
     "colab": {
       "provenance": [],
-      "authorship_tag": "ABX9TyPXPDEQiwNw+kYhWfg4kjz6",
+      "authorship_tag": "ABX9TyPAKqlf9VxztHXKylyJwqe8",
       "include_colab_link": true
     },
     "kernelspec": {
@@ -145,7 +145,7 @@
       "source": [
         "def volume_of_hypersphere(diameter, dimensions):\n",
         "  # Formula given in Problem 8.7 of the book\n",
-        "  # You will need sci.special.gamma()\n",
+        "  # You will need sci.gamma()\n",
         "  # Check out:    https://docs.scipy.org/doc/scipy/reference/generated/scipy.special.gamma.html\n",
         "  # Also use this value for pi\n",
         "  pi = np.pi\n",

Notebooks/Chap09/9_1_L2_Regularization.ipynb

@@ -120,7 +120,7 @@
     {
       "cell_type": "code",
       "source": [
-        "# Initialize the parmaeters and draw the model\n",
+        "# Initialize the parameters and draw the model\n",
         "phi = np.zeros((2,1))\n",
         "phi[0] =  -5     # Horizontal offset\n",
         "phi[1] =  25     # Frequency\n",

Notebooks/Chap09/9_3_Ensembling.ipynb

@@ -4,7 +4,7 @@
   "metadata": {
     "colab": {
       "provenance": [],
-      "authorship_tag": "ABX9TyNuR7X+PMWRddy+WQr4gr5f",
+      "authorship_tag": "ABX9TyOAC7YLEqN5qZhJXqRj+aHB",
       "include_colab_link": true
     },
     "kernelspec": {
@@ -184,7 +184,9 @@
         "  A = np.ones((n_data, n_hidden+1))\n",
         "  for i in range(n_data):\n",
         "      for j in range(1,n_hidden+1):\n",
+        "          # Compute preactivation\n",
         "          A[i,j] = x[i]-(j-1)/n_hidden\n",
+        "          # Apply the ReLU function\n",
         "          if A[i,j] < 0:\n",
         "              A[i,j] = 0;\n",
         "\n",

Notebooks/Chap09/9_4_Bayesian_Approach.ipynb

@@ -1,33 +1,22 @@
 {
-  "nbformat": 4,
-  "nbformat_minor": 0,
-  "metadata": {
-    "colab": {
-      "provenance": [],
-      "authorship_tag": "ABX9TyMB8B4269DVmrcLoCWrhzKF",
-      "include_colab_link": true
-    },
-    "kernelspec": {
-      "name": "python3",
-      "display_name": "Python 3"
-    },
-    "language_info": {
-      "name": "python"
-    }
-  },
   "cells": [
     {
+      "attachments": {},
       "cell_type": "markdown",
       "metadata": {
-        "id": "view-in-github",
+        "colab_type": "text",
-        "colab_type": "text"
+        "id": "view-in-github"
       },
       "source": [
         "<a href=\"https://colab.research.google.com/github/udlbook/udlbook/blob/main/Notebooks/Chap09/9_4_Bayesian_Approach.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
       ]
     },
     {
+      "attachments": {},
       "cell_type": "markdown",
+      "metadata": {
+        "id": "el8l05WQEO46"
+      },
       "source": [
         "# **Notebook 9.4: Bayesian approach**\n",
         "\n",
@@ -36,10 +25,7 @@
         "Work through the cells below, running each cell in turn. In various places you will see the words \"TO DO\". Follow the instructions at these places and make predictions about what is going to happen or write code to complete the functions.\n",
         "\n",
         "Contact me at udlbookmail@gmail.com if you find any mistakes or have any suggestions.\n"
-      ],
+      ]
-      "metadata": {
-        "id": "el8l05WQEO46"
-      }
     },
     {
       "cell_type": "code",
@@ -58,20 +44,25 @@
     },
     {
       "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "3hpqmFyQNrbt"
+      },
+      "outputs": [],
       "source": [
         "# The true function that we are trying to estimate, defined on [0,1]\n",
         "def true_function(x):\n",
         "    y = np.exp(np.sin(x*(2*3.1413)))\n",
         "    return y"
-      ],
+      ]
-      "metadata": {
-        "id": "3hpqmFyQNrbt"
-      },
-      "execution_count": null,
-      "outputs": []
     },
     {
       "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "skZMM5TbNwq4"
+      },
+      "outputs": [],
       "source": [
         "# Generate some data points with or without noise\n",
         "def generate_data(n_data, sigma_y=0.3):\n",
@@ -80,21 +71,21 @@
         "    for i in range(n_data):\n",
         "        x[i] = np.random.uniform(i/n_data, (i+1)/n_data, 1)\n",
         "\n",
-        "    # y value from running through functoin and adding noise\n",
+        "    # y value from running through function and adding noise\n",
         "    y = np.ones(n_data)\n",
         "    for i in range(n_data):\n",
         "        y[i] = true_function(x[i])\n",
         "        y[i] += np.random.normal(0, sigma_y, 1)\n",
         "    return x,y"
-      ],
+      ]
-      "metadata": {
-        "id": "skZMM5TbNwq4"
-      },
-      "execution_count": null,
-      "outputs": []
     },
     {
       "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "ziwD_R7lN0DY"
+      },
+      "outputs": [],
       "source": [
         "# Draw the fitted function, together win uncertainty used to generate points\n",
         "def plot_function(x_func, y_func, x_data=None,y_data=None, x_model = None, y_model =None, sigma_func = None, sigma_model=None):\n",
@@ -117,15 +108,15 @@
         "    ax.set_xlabel('Input, $x$')\n",
         "    ax.set_ylabel('Output, $y$')\n",
         "    plt.show()"
-      ],
+      ]
-      "metadata": {
-        "id": "ziwD_R7lN0DY"
-      },
-      "execution_count": null,
-      "outputs": []
     },
     {
       "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "2CgKanwaN3NM"
+      },
+      "outputs": [],
       "source": [
         "# Generate true function\n",
         "x_func = np.linspace(0, 1.0, 100)\n",
@@ -137,17 +128,17 @@
         "n_data = 15\n",
         "x_data,y_data = generate_data(n_data, sigma_func)\n",
         "\n",
-        "# Plot the functinon, data and uncertainty\n",
+        "# Plot the function, data and uncertainty\n",
         "plot_function(x_func, y_func, x_data, y_data, sigma_func=sigma_func)"
-      ],
+      ]
-      "metadata": {
-        "id": "2CgKanwaN3NM"
-      },
-      "execution_count": null,
-      "outputs": []
     },
     {
       "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "gorZ6i97N7AR"
+      },
+      "outputs": [],
       "source": [
         "# Define model -- beta is a scalar and omega has size n_hidden,1\n",
         "def network(x, beta, omega):\n",
@@ -165,15 +156,14 @@
         "    y = y + beta\n",
         "\n",
         "    return y"
-      ],
+      ]
-      "metadata": {
-        "id": "gorZ6i97N7AR"
-      },
-      "execution_count": null,
-      "outputs": []
     },
     {
+      "attachments": {},
       "cell_type": "markdown",
+      "metadata": {
+        "id": "i8T_QduzeBmM"
+      },
       "source": [
         "Now let's compute a probability distribution over the model parameters using Bayes's rule:\n",
         "\n",
@@ -184,69 +174,73 @@
         "We'll define the prior $Pr(\\boldsymbol\\phi)$ as:\n",
         "\n",
         "\\begin{equation}\n",
-        "Pr(\\boldsymbol\\phi) = \\mbox{Norm}_{\\boldsymbol\\phi}\\bigl[\\mathbf{0},\\sigma^2_p\\mathbf{I}\\bigr]\n",
+        "Pr(\\boldsymbol\\phi) = \\text{Norm}_{\\boldsymbol\\phi}\\bigl[\\mathbf{0},\\sigma^2_p\\mathbf{I}\\bigr]\n",
         "\\end{equation}\n",
         "\n",
         "where $\\phi=[\\omega_1,\\omega_2\\ldots \\omega_n, \\beta]^T$ and $\\sigma^2_{p}$  is the prior variance.\n",
         "\n",
         "The likelihood term $\\prod_{i=1}^{I} Pr(\\mathbf{y}_{i}|\\mathbf{x}_{i},\\boldsymbol\\phi)$ is given by:\n",
         "\n",
-        "\\begin{eqnarray}\n",
+        "\\begin{align}\n",
-        "\\prod_{i=1}^{I} Pr(\\mathbf{y}_{i}|\\mathbf{x}_{i},\\boldsymbol\\phi) &=& \\prod_{i=1}^{I} \\mbox{Norm}_{y_i}\\bigl[\\mbox{f}[\\mathbf{x}_{i},\\boldsymbol\\phi],\\sigma_d^2\\bigr]\\\\\n",
+        "\\prod_{i=1}^{I} Pr(\\mathbf{y}_{i}|\\mathbf{x}_{i},\\boldsymbol\\phi) &=& \\prod_{i=1}^{I} \\text{Norm}_{y_i}\\bigl[\\text{f}[\\mathbf{x}_{i},\\boldsymbol\\phi],\\sigma_d^2\\bigr]\\\\\n",
-        "&=& \\prod_{i=1}^{I} \\mbox{Norm}_{y_i}\\bigl[\\boldsymbol\\omega\\mathbf{h}_i+\\beta,\\sigma_d^2\\bigr]\\\\\n",
+        "&=& \\prod_{i=1}^{I} \\text{Norm}_{y_i}\\bigl[\\boldsymbol\\omega\\mathbf{h}_i+\\beta,\\sigma_d^2\\bigr]\\\\\n",
-        "&=& \\mbox{Norm}_{\\mathbf{y}}\\bigl[\\mathbf{H}^T\\boldsymbol\\phi,\\sigma^2\\mathbf{I}\\bigr].\n",
+        "&=& \\text{Norm}_{\\mathbf{y}}\\bigl[\\mathbf{H}^T\\boldsymbol\\phi,\\sigma^2\\mathbf{I}\\bigr].\n",
-        "\\end{eqnarray}\n",
+        "\\end{align}\n",
         "\n",
         "where $\\sigma^2$ is the measurement noise and $\\mathbf{h}_{i}$ is the column vector of hidden variables for the $i^{th}$ input.  Here the vector $\\mathbf{y}$ and matrix $\\mathbf{H}$ are defined as:\n",
         "\n",
         "\\begin{equation}\n",
-        "\\mathbf{y} = \\begin{bmatrix}y_1\\\\y_2\\\\\\vdots\\\\y_{I}\\end{bmatrix}\\quad\\mbox{and}\\quad \\mathbf{H} = \\begin{bmatrix}\\mathbf{h}_{1}&\\mathbf{h}_{2}&\\cdots&\\mathbf{h}_{I}\\\\1&1&\\cdots &1\\end{bmatrix}.\n",
+        "\\mathbf{y} = \\begin{bmatrix}y_1\\\\y_2\\\\\\vdots\\\\y_{I}\\end{bmatrix}\\quad\\text{and}\\quad \\mathbf{H} = \\begin{bmatrix}\\mathbf{h}_{1}&\\mathbf{h}_{2}&\\cdots&\\mathbf{h}_{I}\\\\1&1&\\cdots &1\\end{bmatrix}.\n",
         "\\end{equation}\n"
-      ],
+      ]
-      "metadata": {
-        "id": "i8T_QduzeBmM"
-      }
     },
     {
+      "attachments": {},
       "cell_type": "markdown",
+      "metadata": {
+        "id": "JojV6ueRk49G"
+      },
       "source": [
         "To make progress we use the change of variable relation (Appendix C.3.4 of the book) to rewrite the likelihood term as a normal distribution in the parameters $\\boldsymbol\\phi$:\n",
         "\n",
-        "\\begin{eqnarray}\n",
+        "\\begin{align}\n",
         "\\prod_{i=1}^{I} Pr(\\mathbf{y}_{i}|\\mathbf{x}_{i},\\boldsymbol\\phi+\\beta)\n",
-        "&=& \\mbox{Norm}_{\\mathbf{y}}\\bigl[\\mathbf{H}^T\\boldsymbol\\phi,\\sigma^2\\bigr]\\\\\n",
+        "&=& \\text{Norm}_{\\mathbf{y}}\\bigl[\\mathbf{H}^T\\boldsymbol\\phi,\\sigma^2\\bigr]\\\\\n",
-        "&\\propto& \\mbox{Norm}_{\\boldsymbol\\phi}\\bigl[(\\mathbf{H}\\mathbf{H}^T)^{-1}\\mathbf{H}\\mathbf{y},\\sigma^2(\\mathbf{H}\\mathbf{H}^t)^{-1}\\bigr]\n",
+        "&\\propto& \\text{Norm}_{\\boldsymbol\\phi}\\bigl[(\\mathbf{H}\\mathbf{H}^T)^{-1}\\mathbf{H}\\mathbf{y},\\sigma^2(\\mathbf{H}\\mathbf{H}^t)^{-1}\\bigr]\n",
-        "\\end{eqnarray}\n"
+        "\\end{align}\n"
-      ],
+      ]
-      "metadata": {
-        "id": "JojV6ueRk49G"
-      }
     },
     {
+      "attachments": {},
       "cell_type": "markdown",
+      "metadata": {
+        "id": "YX0O_Ciwp4W1"
+      },
       "source": [
         "Finally, we can combine the likelihood and prior terms using the product of two normal distributions relation (Appendix C.3.3).\n",
         "\n",
-        "\\begin{eqnarray}\n",
+        "\\begin{align}\n",
         " Pr(\\boldsymbol\\phi|\\{\\mathbf{x}_{i},\\mathbf{y}_{i}\\}) &\\propto& \\prod_{i=1}^{I} Pr(\\mathbf{y}_{i}|\\mathbf{x}_{i},\\boldsymbol\\phi) Pr(\\boldsymbol\\phi)\\\\\n",
-        " &\\propto&\\mbox{Norm}_{\\boldsymbol\\phi}\\bigl[(\\mathbf{H}\\mathbf{H}^T)^{-1}\\mathbf{H}\\mathbf{y},\\sigma^2(\\mathbf{H}\\mathbf{H}^T)^{-1}\\bigr] \\mbox{Norm}_{\\boldsymbol\\phi}\\bigl[\\mathbf{0},\\sigma^2_p\\mathbf{I}\\bigr]\\\\\n",
+        " &\\propto&\\text{Norm}_{\\boldsymbol\\phi}\\bigl[(\\mathbf{H}\\mathbf{H}^T)^{-1}\\mathbf{H}\\mathbf{y},\\sigma^2(\\mathbf{H}\\mathbf{H}^T)^{-1}\\bigr] \\text{Norm}_{\\boldsymbol\\phi}\\bigl[\\mathbf{0},\\sigma^2_p\\mathbf{I}\\bigr]\\\\\n",
-        " &\\propto&\\mbox{Norm}_{\\boldsymbol\\phi}\\biggl[\\frac{1}{\\sigma^2}\\left(\\frac{1}{\\sigma^2}\\mathbf{H}\\mathbf{H}^T+\\frac{1}{\\sigma_p^2}\\mathbf{I}\\right)^{-1}\\mathbf{H}\\mathbf{y},\\left(\\frac{1}{\\sigma^2}\\mathbf{H}\\mathbf{H}^T+\\frac{1}{\\sigma_p^2}\\mathbf{I}\\right)^{-1}\\biggr].\n",
+        " &\\propto&\\text{Norm}_{\\boldsymbol\\phi}\\biggl[\\frac{1}{\\sigma^2}\\left(\\frac{1}{\\sigma^2}\\mathbf{H}\\mathbf{H}^T+\\frac{1}{\\sigma_p^2}\\mathbf{I}\\right)^{-1}\\mathbf{H}\\mathbf{y},\\left(\\frac{1}{\\sigma^2}\\mathbf{H}\\mathbf{H}^T+\\frac{1}{\\sigma_p^2}\\mathbf{I}\\right)^{-1}\\biggr].\n",
-        "\\end{eqnarray}\n",
+        "\\end{align}\n",
         "\n",
         "In fact, since this already a normal distribution, the constant of proportionality must be one and we can write\n",
         "\n",
-        "\\begin{eqnarray}\n",
+        "\\begin{align}\n",
-        " Pr(\\boldsymbol\\phi|\\{\\mathbf{x}_{i},\\mathbf{y}_{i}\\}) &=& \\mbox{Norm}_{\\boldsymbol\\phi}\\biggl[\\frac{1}{\\sigma^2}\\left(\\frac{1}{\\sigma^2}\\mathbf{H}\\mathbf{H}^T+\\frac{1}{\\sigma_p^2}\\mathbf{I}\\right)^{-1}\\mathbf{H}\\mathbf{y},\\left(\\frac{1}{\\sigma^2}\\mathbf{H}\\mathbf{H}^T+\\frac{1}{\\sigma_p^2}\\mathbf{I}\\right)^{-1}\\biggr].\n",
+        " Pr(\\boldsymbol\\phi|\\{\\mathbf{x}_{i},\\mathbf{y}_{i}\\}) &=& \\text{Norm}_{\\boldsymbol\\phi}\\biggl[\\frac{1}{\\sigma^2}\\left(\\frac{1}{\\sigma^2}\\mathbf{H}\\mathbf{H}^T+\\frac{1}{\\sigma_p^2}\\mathbf{I}\\right)^{-1}\\mathbf{H}\\mathbf{y},\\left(\\frac{1}{\\sigma^2}\\mathbf{H}\\mathbf{H}^T+\\frac{1}{\\sigma_p^2}\\mathbf{I}\\right)^{-1}\\biggr].\n",
-        "\\end{eqnarray}\n",
+        "\\end{align}\n",
         "\n",
         "TODO -- On a piece of paper, use the relations in Appendix C.3.3 and C.3.4 to fill in the missing steps and establish that this is the correct formula for the posterior."
-      ],
+      ]
-      "metadata": {
-        "id": "YX0O_Ciwp4W1"
-      }
     },
     {
       "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "nF1AcgNDwm4t"
+      },
+      "outputs": [],
       "source": [
         "def compute_H(x_data, n_hidden):\n",
         "  psi1 = np.ones((n_hidden+1,1));\n",
@@ -280,24 +274,25 @@
         "\n",
         "\n",
         "  return phi_mean, phi_covar"
-      ],
+      ]
-      "metadata": {
-        "id": "nF1AcgNDwm4t"
-      },
-      "execution_count": null,
-      "outputs": []
     },
     {
+      "attachments": {},
       "cell_type": "markdown",
-      "source": [
-        "Now we can draw samples from this distribution"
-      ],
       "metadata": {
         "id": "GjPnlG4q0UFK"
-      }
+      },
+      "source": [
+        "Now we can draw samples from this distribution"
+      ]
     },
     {
       "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "K4vYc82D0BMq"
+      },
+      "outputs": [],
       "source": [
         "# Define parameters\n",
         "n_hidden = 5\n",
@@ -313,15 +308,15 @@
         "x_model = x_func\n",
         "y_model_mean = network(x_model, phi_mean[-1], phi_mean[0:n_hidden])\n",
         "plot_function(x_func, y_func, x_data, y_data, x_model, y_model_mean)"
-      ],
+      ]
-      "metadata": {
-        "id": "K4vYc82D0BMq"
-      },
-      "execution_count": null,
-      "outputs": []
     },
     {
       "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "TVIjhubkSw-R"
+      },
+      "outputs": [],
       "source": [
         "# TODO Draw two samples from the normal distribution over the parameters\n",
         "# Replace these lines\n",
@@ -336,37 +331,42 @@
         "# Draw the two models\n",
         "plot_function(x_func, y_func, x_data, y_data, x_model, y_model_sample1)\n",
         "plot_function(x_func, y_func, x_data, y_data, x_model, y_model_sample2)"
-      ],
+      ]
-      "metadata": {
-        "id": "TVIjhubkSw-R"
-      },
-      "execution_count": null,
-      "outputs": []
     },
     {
+      "attachments": {},
       "cell_type": "markdown",
+      "metadata": {
+        "id": "GiNg5EroUiUb"
+      },
       "source": [
         "Now we need to perform inference for a new data points $\\mathbf{x}^*$ with corresponding hidden values $\\mathbf{h}^*$.  Instead of having a single estimate of the parameters, we have a distribution over the possible parameters.  So we marginalize (integrate) over this distribution to account for all possible values:\n",
         "\n",
-        "\\begin{eqnarray}\n",
+        "\\begin{align}\n",
         "Pr(y^*|\\mathbf{x}^*)  &=& \\int Pr(y^{*}|\\mathbf{x}^*,\\boldsymbol\\phi)Pr(\\boldsymbol\\phi|\\{\\mathbf{x}_{i},\\mathbf{y}_{i}\\}) d\\boldsymbol\\phi\\\\\n",
-        "&=& \\int \\mbox{Norm}_{y^*}\\bigl[\\begin{bmatrix}\\mathbf{h}^{*T}&1\\end{bmatrix}\\boldsymbol\\phi,\\sigma^2]\\cdot\\mbox{Norm}_{\\boldsymbol\\phi}\\biggl[\\frac{1}{\\sigma^2}\\left(\\frac{1}{\\sigma^2}\\mathbf{H}\\mathbf{H}^T+\\frac{1}{\\sigma_p^2}\\mathbf{I}\\right)^{-1}\\mathbf{H}\\mathbf{y},\\left(\\frac{1}{\\sigma^2}\\mathbf{H}\\mathbf{H}^T+\\frac{1}{\\sigma_p^2}\\mathbf{I}\\right)^{-1}\\biggr]d\\boldsymbol\\phi\\\\\n",
+        "&=& \\int \\text{Norm}_{y^*}\\bigl[[\\mathbf{h}^{*T},1]\\boldsymbol\\phi,\\sigma^2\\bigr]\\cdot\\text{Norm}_{\\boldsymbol\\phi}\\biggl[\\frac{1}{\\sigma^2}\\left(\\frac{1}{\\sigma^2}\\mathbf{H}\\mathbf{H}^T+\\frac{1}{\\sigma_p^2}\\mathbf{I}\\right)^{-1}\\mathbf{H}\\mathbf{y},\\left(\\frac{1}{\\sigma^2}\\mathbf{H}\\mathbf{H}^T+\\frac{1}{\\sigma_p^2}\\mathbf{I}\\right)^{-1}\\biggr]d\\boldsymbol\\phi\\\\\n",
-        "&=& \\mbox{Norm}_{y^*}\\biggl[\\frac{1}{\\sigma^2} \\begin{bmatrix}\\mathbf{h}^{*T}&1\\end{bmatrix}\\left(\\frac{1}{\\sigma^2}\\mathbf{H}\\mathbf{H}^T+\\frac{1}{\\sigma_p^2}\\mathbf{I}\\right)^{-1}\\mathbf{H}\\mathbf{y},  \\begin{bmatrix}\\mathbf{h}^{*T}&1\\end{bmatrix}\\left(\\frac{1}{\\sigma^2}\\mathbf{H}\\mathbf{H}^T+\\frac{1}{\\sigma_p^2}\\mathbf{I}\\right)^{-1}\n",
+        "&=& \\text{Norm}_{y^*}\\biggl[\\frac{1}{\\sigma^2} [\\mathbf{h}^{*T},1]\\left(\\frac{1}{\\sigma^2}\\mathbf{H}\\mathbf{H}^T+\\frac{1}{\\sigma_p^2}\\mathbf{I}\\right)^{-1}\\mathbf{H}\\mathbf{y},  [\\mathbf{h}^{*T},1]\\left(\\frac{1}{\\sigma^2}\\mathbf{H}\\mathbf{H}^T+\\frac{1}{\\sigma_p^2}\\mathbf{I}\\right)^{-1}\n",
-        "\\begin{bmatrix}\\mathbf{h}^*\\\\1\\end{bmatrix}\\biggr]\n",
+        "[\\mathbf{h}^*;1]\\biggr]\n",
-        "\\end{eqnarray}\n",
+        "\\end{align}\n",
+        "\n",
+        "\n",
+        "\n",
         "\n",
         "To compute this, we reformulated the integrand using the relations from appendices\n",
         "C.3.3 and C.3.4 as the product of a normal distribution in $\\boldsymbol\\phi$ and a constant with respect\n",
-        "to $\\boldsymbol\\phi$. The integral of the normal distribution must be one, and so the finnal result is just the constant. This constant is itself a normal distribution in $y^*$. <br>\n",
+        "to $\\boldsymbol\\phi$. The integral of the normal distribution must be one, and so the final result is just the constant. This constant is itself a normal distribution in $y^*$. <br>\n",
         "\n",
-        "If you feel so inclined you can work through the math of this yourself."
+        "If you feel so inclined you can work through the math of this yourself.\n",
-      ],
+        "\n"
-      "metadata": {
+      ]
-        "id": "GiNg5EroUiUb"
-      }
     },
     {
       "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "ILxT4EfW2lUm"
+      },
+      "outputs": [],
       "source": [
         "# Predict mean and variance of y_star from x_star\n",
         "def inference(x_star, x_data, y_data, sigma_sq, sigma_p_sq, n_hidden):\n",
@@ -381,15 +381,15 @@
         "  y_star_var =  1\n",
         "\n",
         "  return y_star_mean, y_star_var"
-      ],
+      ]
-      "metadata": {
-        "id": "ILxT4EfW2lUm"
-      },
-      "execution_count": null,
-      "outputs": []
     },
     {
       "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "87cjUjMaixHZ"
+      },
+      "outputs": [],
       "source": [
         "x_model = x_func\n",
         "y_model = np.zeros_like(x_model)\n",
@@ -401,24 +401,36 @@
         "\n",
         "# Draw the model\n",
         "plot_function(x_func, y_func, x_data, y_data, x_model, y_model, sigma_model=y_model_std)\n"
-      ],
+      ]
-      "metadata": {
-        "id": "87cjUjMaixHZ"
-      },
-      "execution_count": null,
-      "outputs": []
     },
     {
+      "attachments": {},
       "cell_type": "markdown",
+      "metadata": {
+        "id": "8Hcbe_16sK0F"
+      },
       "source": [
         "TODO:\n",
         "\n",
         "1.  Experiment running this again with different numbers of hidden units.  Make a prediction for what will happen when you increase / decrease them.\n",
         "2.  Experiment with what happens if you make the prior variance $\\sigma^2_p$ to a smaller value like 1.  How do you explain the results?"
-      ],
+      ]
-      "metadata": {
-        "id": "8Hcbe_16sK0F"
-      }
     }
-  ]
+  ],
-}
+  "metadata": {
+    "colab": {
+      "authorship_tag": "ABX9TyMB8B4269DVmrcLoCWrhzKF",
+      "include_colab_link": true,
+      "provenance": []
+    },
+    "kernelspec": {
+      "display_name": "Python 3",
+      "name": "python3"
+    },
+    "language_info": {
+      "name": "python"
+    }
+  },
+  "nbformat": 4,
+  "nbformat_minor": 0
+}

Notebooks/Chap09/9_5_Augmentation.ipynb

@@ -4,7 +4,7 @@
   "metadata": {
     "colab": {
       "provenance": [],
-      "authorship_tag": "ABX9TyM3wq9CHLjekkIXIgXRxueE",
+      "authorship_tag": "ABX9TyM38ZVBK4/xaHk5Ys5lF6dN",
       "include_colab_link": true
     },
     "kernelspec": {
@@ -208,14 +208,14 @@
     {
       "cell_type": "code",
       "source": [
-        "def augment(data_in):\n",
+        "def augment(input_vector):\n",
         "  # Create output vector\n",
-        "  data_out = np.zeros_like(data_in)\n",
+        "  data_out = np.zeros_like(input_vector)\n",
         "\n",
         "  # TODO:  Shift the input data by a random offset\n",
         "  # (rotating, so points that would go off the end, are added back to the beginning)\n",
         "  # Replace this line:\n",
-        "  data_out = np.zeros_like(data_in) ;\n",
+        "  data_out = np.zeros_like(input_vector) ;\n",
         "\n",
         "  # TODO:    # Randomly scale the data by a factor drawn from a uniform distribution over [0.8,1.2]\n",
         "  # Replace this line:\n",

Notebooks/Chap10/10_1_1D_Convolution.ipynb

@@ -4,7 +4,7 @@
   "metadata": {
     "colab": {
       "provenance": [],
-      "authorship_tag": "ABX9TyPHUNRkJMI5LujaxIXNV60m",
+      "authorship_tag": "ABX9TyML7rfAGE4gvmNUEiK5x3PS",
       "include_colab_link": true
     },
     "kernelspec": {
@@ -41,6 +41,17 @@
         "id": "el8l05WQEO46"
       }
     },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "NOTE!!\n",
+        "\n",
+        "If you have the first edition of the printed book, it mistakenly refers to a convolutional filter with no spaces between the elements (i.e. a normal filter without dilation) as having dilation zero.  Actually, the convention is (weirdly) that this has dilation one.  And when there is one space between the elements, this is dilation two.   This notebook reflects the correct convention and so will be out of sync with the printed book.  If this is confusing, check the [errata](https://github.com/udlbook/udlbook/blob/main/UDL_Errata.pdf) document."
+      ],
+      "metadata": {
+        "id": "ggQrHkFZcUiV"
+      }
+    },
     {
       "cell_type": "code",
       "source": [
@@ -50,7 +61,7 @@
       "metadata": {
         "id": "nw7k5yCtOzoK"
       },
-      "execution_count": null,
+      "execution_count": 1,
       "outputs": []
     },
     {
@@ -85,10 +96,10 @@
       "cell_type": "code",
       "source": [
         "# Now let's define a zero-padded convolution operation\n",
-        "# with a convolution kernel size of 3, a stride of 1, and a dilation of 0\n",
+        "# with a convolution kernel size of 3, a stride of 1, and a dilation of 1\n",
         "# as in figure 10.2a-c.  Write it yourself, don't call a library routine!\n",
         "# Don't forget that Python arrays are indexed from zero, not from 1 as in the book figures\n",
-        "def conv_3_1_0_zp(x_in, omega):\n",
+        "def conv_3_1_1_zp(x_in, omega):\n",
         "    x_out = np.zeros_like(x_in)\n",
         "    # TODO -- write this function\n",
         "    # replace this line\n",
@@ -119,7 +130,7 @@
       "source": [
         "\n",
         "omega = [0.33,0.33,0.33]\n",
-        "h = conv_3_1_0_zp(x, omega)\n",
+        "h = conv_3_1_1_zp(x, omega)\n",
         "\n",
         "# Check that you have computed this correctly\n",
         "print(f\"Sum of output is {np.sum(h):3.3}, should be 71.1\")\n",
@@ -155,7 +166,7 @@
       "source": [
         "\n",
         "omega = [-0.5,0,0.5]\n",
-        "h2 = conv_3_1_0_zp(x, omega)\n",
+        "h2 = conv_3_1_1_zp(x, omega)\n",
         "\n",
         "# Draw the signal\n",
         "fig,ax = plt.subplots()\n",
@@ -187,9 +198,9 @@
       "cell_type": "code",
       "source": [
         "# Now let's define a zero-padded convolution operation\n",
-        "# with a convolution kernel size of 3, a stride of 2, and a dilation of 0\n",
+        "# with a convolution kernel size of 3, a stride of 2, and a dilation of 1\n",
-        "# as in figure 10.2a-c.  Write it yourself, don't call a library routine!\n",
+        "# as in figure 10.3a-b.  Write it yourself, don't call a library routine!\n",
-        "def conv_3_2_0_zp(x_in, omega):\n",
+        "def conv_3_2_1_zp(x_in, omega):\n",
         "    x_out = np.zeros(int(np.ceil(len(x_in)/2)))\n",
         "    # TODO -- write this function\n",
         "    # replace this line\n",
@@ -209,7 +220,7 @@
       "cell_type": "code",
       "source": [
         "omega = [0.33,0.33,0.33]\n",
-        "h3 = conv_3_2_0_zp(x, omega)\n",
+        "h3 = conv_3_2_1_zp(x, omega)\n",
         "\n",
         "# If you have done this right, the output length should be six and it should\n",
         "# contain every other value from the original convolution with stride 1\n",
@@ -226,9 +237,9 @@
       "cell_type": "code",
       "source": [
         "# Now let's define a zero-padded convolution operation\n",
-        "# with a convolution kernel size of 5, a stride of 1, and a dilation of 0\n",
+        "# with a convolution kernel size of 5, a stride of 1, and a dilation of 1\n",
-        "# as in figure 10.2a-c.  Write it yourself, don't call a library routine!\n",
+        "# as in figure 10.3c.  Write it yourself, don't call a library routine!\n",
-        "def conv_5_1_0_zp(x_in, omega):\n",
+        "def conv_5_1_1_zp(x_in, omega):\n",
         "    x_out = np.zeros_like(x_in)\n",
         "    # TODO -- write this function\n",
         "    # replace this line\n",
@@ -249,7 +260,7 @@
       "source": [
         "\n",
         "omega2 = [0.2, 0.2, 0.2, 0.2, 0.2]\n",
-        "h4 = conv_5_1_0_zp(x, omega2)\n",
+        "h4 = conv_5_1_1_zp(x, omega2)\n",
         "\n",
         "# Check that you have computed this correctly\n",
         "print(f\"Sum of output is {np.sum(h4):3.3}, should be 69.6\")\n",
@@ -273,10 +284,10 @@
       "cell_type": "code",
       "source": [
         "# Finally let's define a zero-padded convolution operation\n",
-        "# with a convolution kernel size of 3, a stride of 1, and a dilation of 1\n",
+        "# with a convolution kernel size of 3, a stride of 1, and a dilation of 2\n",
-        "# as in figure 10.2a-c.  Write it yourself, don't call a library routine!\n",
+        "# as in figure 10.3d.  Write it yourself, don't call a library routine!\n",
         "# Don't forget that Python arrays are indexed from zero, not from 1 as in the book figures\n",
-        "def conv_3_1_1_zp(x_in, omega):\n",
+        "def conv_3_1_2_zp(x_in, omega):\n",
         "    x_out = np.zeros_like(x_in)\n",
         "    # TODO -- write this function\n",
         "    # replace this line\n",
@@ -295,7 +306,7 @@
       "cell_type": "code",
       "source": [
         "omega = [0.33,0.33,0.33]\n",
-        "h5 = conv_3_1_1_zp(x, omega)\n",
+        "h5 = conv_3_1_2_zp(x, omega)\n",
         "\n",
         "# Check that you have computed this correctly\n",
         "print(f\"Sum of output is {np.sum(h5):3.3}, should be 68.3\")\n",
@@ -328,9 +339,9 @@
       "cell_type": "code",
       "source": [
         "# Compute matrix in figure 10.4 d\n",
-        "def get_conv_mat_3_1_0_zp(n_out, omega):\n",
+        "def get_conv_mat_3_1_1_zp(n_out, omega):\n",
         "  omega_mat = np.zeros((n_out,n_out))\n",
-        "  # TODO Fill in this matix\n",
+        "  # TODO Fill in this matrix\n",
         "  # Replace this line:\n",
         "  omega_mat = omega_mat\n",
         "\n",
@@ -349,11 +360,11 @@
       "source": [
         "# Run original convolution\n",
         "omega = np.array([-1.0,0.5,-0.2])\n",
-        "h6 = conv_3_1_0_zp(x, omega)\n",
+        "h6 = conv_3_1_1_zp(x, omega)\n",
         "print(h6)\n",
         "\n",
         "# If you have done this right, you should get the same answer\n",
-        "omega_mat = get_conv_mat_3_1_0_zp(len(x), omega)\n",
+        "omega_mat = get_conv_mat_3_1_1_zp(len(x), omega)\n",
         "h7 = np.matmul(omega_mat, x)\n",
         "print(h7)\n"
       ],
@@ -373,4 +384,4 @@
       }
     }
   ]
-}
+}

Notebooks/Chap10/10_2_Convolution_for_MNIST_1D.ipynb

@@ -4,7 +4,7 @@
   "metadata": {
     "colab": {
       "provenance": [],
-      "authorship_tag": "ABX9TyOgDisWDe/zHpfTGCH8AZ3i",
+      "authorship_tag": "ABX9TyNJodaaCLMRWL9vTl8B/iLI",
       "include_colab_link": true
     },
     "kernelspec": {
@@ -128,11 +128,11 @@
         "\n",
         "\n",
         "# TODO Create a model with the following layers\n",
-        "# 1. Convolutional layer, (input=length 40 and 1 channel, kernel size 3x3, stride 2, padding=\"valid\", 15 output channels )\n",
+        "# 1. Convolutional layer, (input=length 40 and 1 channel, kernel size 3, stride 2, padding=\"valid\", 15 output channels )\n",
         "# 2. ReLU\n",
-        "# 3. Convolutional layer, (input=length 19 and 15 channels, kernel size 3x3, stride 2, padding=\"valid\", 15 output channels )\n",
+        "# 3. Convolutional layer, (input=length 19 and 15 channels, kernel size 3, stride 2, padding=\"valid\", 15 output channels )\n",
         "# 4. ReLU\n",
-        "# 5. Convolutional layer, (input=length 9 and 15 channels, kernel size 3x3, stride 2, padding=\"valid\", 15 output channels)\n",
+        "# 5. Convolutional layer, (input=length 9 and 15 channels, kernel size 3, stride 2, padding=\"valid\", 15 output channels)\n",
         "# 6. ReLU\n",
         "# 7. Flatten (converts 4x15) to length 60\n",
         "# 8. Linear layer (input size = 60, output size = 10)\n",
@@ -141,6 +141,9 @@
         "# https://pytorch.org/docs/stable/generated/torch.nn.Flatten.html\n",
         "# https://pytorch.org/docs/1.13/generated/torch.nn.Linear.html?highlight=linear#torch.nn.Linear\n",
         "\n",
+        "# NOTE THAT THE CONVOLUTIONAL LAYERS NEED TO TAKE THE NUMBER OF INPUT CHANNELS AS A PARAMETER\n",
+        "# AND NOT THE INPUT SIZE.\n",
+        "\n",
         "# Replace the following function:\n",
         "model = nn.Sequential(\n",
         "nn.Flatten(),\n",
@@ -185,9 +188,9 @@
         "scheduler = StepLR(optimizer, step_size=20, gamma=0.5)\n",
         "# create 100 dummy data points and store in data loader class\n",
         "x_train = torch.tensor(train_data_x.transpose().astype('float32'))\n",
-        "y_train = torch.tensor(train_data_y.astype('long'))\n",
+        "y_train = torch.tensor(train_data_y.astype('long')).long()\n",
         "x_val= torch.tensor(val_data_x.transpose().astype('float32'))\n",
-        "y_val = torch.tensor(val_data_y.astype('long'))\n",
+        "y_val = torch.tensor(val_data_y.astype('long')).long()\n",
         "\n",
         "# load the data into a class that creates the batches\n",
         "data_loader = DataLoader(TensorDataset(x_train,y_train), batch_size=100, shuffle=True, worker_init_fn=np.random.seed(1))\n",

Notebooks/Chap10/10_3_2D_Convolution.ipynb

@@ -4,7 +4,7 @@
   "metadata": {
     "colab": {
       "provenance": [],
-      "authorship_tag": "ABX9TyMmbD0cKYvIHXbKX4AupA1x",
+      "authorship_tag": "ABX9TyNDaU2KKZDyY9Ea7vm/fNxo",
       "include_colab_link": true
     },
     "kernelspec": {
@@ -114,6 +114,11 @@
         "    # Create output\n",
         "    out = np.zeros((batchSize, channelsOut, imageHeightOut, imageWidthOut), dtype=np.float32)\n",
         "\n",
+        "    # !!!!!! NOTE THERE IS A SUBTLETY HERE !!!!!!!!\n",
+        "    # I have padded the image with zeros above, so it is surrouned by a \"ring\" of zeros\n",
+        "    # That means that the image indexes are all off by one\n",
+        "    # This actually makes your code simpler\n",
+        "\n",
         "    for c_y in range(imageHeightOut):\n",
         "      for c_x in range(imageWidthOut):\n",
         "        for c_kernel_y in range(kernelHeight):\n",

Notebooks/Chap11/11_2_Residual_Networks.ipynb

@@ -4,7 +4,7 @@
   "metadata": {
     "colab": {
       "provenance": [],
-      "authorship_tag": "ABX9TyObut1y9atNUuowPT6dMY+I",
+      "authorship_tag": "ABX9TyMXS3SPB4cS/4qxix0lH/Hq",
       "include_colab_link": true
     },
     "kernelspec": {
@@ -144,10 +144,10 @@
         "  def count_params(self):\n",
         "    return sum([p.view(-1).shape[0] for p in self.parameters()])\n",
         "\n",
-        "# # TODO -- Add residual connections to this model\n",
+        "# TODO -- Add residual connections to this model\n",
-        "# # The order of operations should similar to figure 11.5b\n",
+        "# The order of operations within each block should similar to figure 11.5b\n",
-        "# # linear1 first, ReLU+linear2 in first residual block, ReLU+linear3 in second residual block), linear4 at end\n",
+        "# ie., linear1 first, ReLU+linear2 in first residual block, ReLU+linear3 in second residual block), linear4 at end\n",
-        "# # Replace this function\n",
+        "# Replace this function\n",
         "  def forward(self, x):\n",
         "    h1 = self.linear1(x).relu()\n",
         "    h2 = self.linear2(h1).relu()\n",

Notebooks/Chap11/11_3_Batch_Normalization.ipynb

@@ -4,7 +4,7 @@
   "metadata": {
     "colab": {
       "provenance": [],
-      "authorship_tag": "ABX9TyOoGS+lY+EhGthebSO4smpj",
+      "authorship_tag": "ABX9TyPVeAd3eDpEOCFh8CVyr1zz",
       "include_colab_link": true
     },
     "kernelspec": {
@@ -205,7 +205,8 @@
         "    self.linear3 = nn.Linear(hidden_size, hidden_size)\n",
         "    self.linear4 = nn.Linear(hidden_size, hidden_size)\n",
         "    self.linear5 = nn.Linear(hidden_size, hidden_size)\n",
-        "    self.linear6 = nn.Linear(hidden_size, output_size)\n",
+        "    self.linear6 = nn.Linear(hidden_size, hidden_size)\n",
+        "    self.linear7 = nn.Linear(hidden_size, output_size)\n",
         "\n",
         "  def count_params(self):\n",
         "    return sum([p.view(-1).shape[0] for p in self.parameters()])\n",
@@ -220,11 +221,11 @@
         "    print_variance(\"After second residual connection\",res2)\n",
         "    res3 = res2 + self.linear4(res2.relu())\n",
         "    print_variance(\"After third residual connection\",res3)\n",
-        "    res4 = res3 + self.linear4(res3.relu())\n",
+        "    res4 = res3 + self.linear5(res3.relu())\n",
         "    print_variance(\"After fourth residual connection\",res4)\n",
-        "    res5 = res4 + self.linear4(res4.relu())\n",
+        "    res5 = res4 + self.linear6(res4.relu())\n",
         "    print_variance(\"After fifth residual connection\",res5)\n",
-        "    return self.linear6(res5)"
+        "    return self.linear7(res5)"
       ],
       "metadata": {
         "id": "FslroPJJffrh"
@@ -272,7 +273,8 @@
         "    self.linear3 = nn.Linear(hidden_size, hidden_size)\n",
         "    self.linear4 = nn.Linear(hidden_size, hidden_size)\n",
         "    self.linear5 = nn.Linear(hidden_size, hidden_size)\n",
-        "    self.linear6 = nn.Linear(hidden_size, output_size)\n",
+        "    self.linear6 = nn.Linear(hidden_size, hidden_size)\n",
+        "    self.linear7 = nn.Linear(hidden_size, output_size)\n",
         "\n",
         "  def count_params(self):\n",
         "    return sum([p.view(-1).shape[0] for p in self.parameters()])\n",
@@ -287,11 +289,11 @@
         "    print_variance(\"After second residual connection\",res2)\n",
         "    res3 = res2 + self.linear4(res2.relu())\n",
         "    print_variance(\"After third residual connection\",res3)\n",
-        "    res4 = res3 + self.linear4(res3.relu())\n",
+        "    res4 = res3 + self.linear5(res3.relu())\n",
         "    print_variance(\"After fourth residual connection\",res4)\n",
-        "    res5 = res4 + self.linear4(res4.relu())\n",
+        "    res5 = res4 + self.linear6(res4.relu())\n",
         "    print_variance(\"After fifth residual connection\",res5)\n",
-        "    return self.linear6(res5)"
+        "    return self.linear7(res5)"
       ],
       "metadata": {
         "id": "5JvMmaRITKGd"

Notebooks/Chap12/12_1_Self_Attention.ipynb

@@ -31,7 +31,7 @@
       "source": [
         "# **Notebook 12.1: Self Attention**\n",
         "\n",
-        "This notebook builds a self-attnetion mechanism from scratch, as discussed in section 12.2 of the book.\n",
+        "This notebook builds a self-attention mechanism from scratch, as discussed in section 12.2 of the book.\n",
         "\n",
         "Work through the cells below, running each cell in turn. In various places you will see the words \"TO DO\". Follow the instructions at these places and make predictions about what is going to happen or write code to complete the functions.\n",
         "\n",
@@ -153,7 +153,7 @@
     {
       "cell_type": "markdown",
       "source": [
-        "We'll need a softmax function (equation 12.5) -- here, it will take a list of arbirtrary numbers and return a list where the elements are non-negative and sum to one\n"
+        "We'll need a softmax function (equation 12.5) -- here, it will take a list of arbitrary numbers and return a list where the elements are non-negative and sum to one\n"
       ],
       "metadata": {
         "id": "Se7DK6PGPSUk"
@@ -364,7 +364,7 @@
     {
       "cell_type": "markdown",
       "source": [
-        "TODO -- Investigate whether the self-attention mechanism is covariant with respect to permulation.\n",
+        "TODO -- Investigate whether the self-attention mechanism is covariant with respect to permutation.\n",
         "If it is, when we permute the columns of the input matrix $\\mathbf{X}$, the columns of the output matrix $\\mathbf{X}'$ will also be permuted.\n"
       ],
       "metadata": {

Notebooks/Chap12/12_2_Multihead_Self_Attention.ipynb

@@ -31,7 +31,7 @@
       "source": [
         "# **Notebook 12.1: Multhead Self-Attention**\n",
         "\n",
-        "This notebook builds a multihead self-attentionm mechanism as in figure 12.6\n",
+        "This notebook builds a multihead self-attention mechanism as in figure 12.6\n",
         "\n",
         "Work through the cells below, running each cell in turn. In various places you will see the words \"TO DO\". Follow the instructions at these places and make predictions about what is going to happen or write code to complete the functions.\n",
         "\n",

Notebooks/Chap12/12_4_Decoding_Strategies.ipynb

@@ -4,7 +4,7 @@
   "metadata": {
     "colab": {
       "provenance": [],
-      "authorship_tag": "ABX9TyNPrHfkLWjy3NfDHRhGG3IE",
+      "authorship_tag": "ABX9TyPsZjfqVeHYh95Hzt+hCIO7",
       "include_colab_link": true
     },
     "kernelspec": {
@@ -409,7 +409,7 @@
         "  print(\"Choosing from %d tokens\"%(thresh_index))\n",
         "  # TODO:  Find the probability value to threshold\n",
         "  # Replace this line:\n",
-        "  thresh_prob = sorted_probs_decreasing[thresh_index]\n",
+        "  thresh_prob = 0.5\n",
         "\n",
         "\n",
         "\n",

Notebooks/Chap13/13_2_Graph_Classification.ipynb

@@ -57,7 +57,7 @@
     {
       "cell_type": "markdown",
       "source": [
-        "Let's build a model that maps a chemical structure to a binary decision.  This model might be used to predict whether a chemical is liquid at room temparature or not.  We'll start by drawing the chemical structure."
+        "Let's build a model that maps a chemical structure to a binary decision.  This model might be used to predict whether a chemical is liquid at room temperature or not.  We'll start by drawing the chemical structure."
       ],
       "metadata": {
         "id": "UNleESc7k5uB"
@@ -191,7 +191,7 @@
       "source": [
         "# Let's test this network\n",
         "f = graph_neural_network(A,X, Omega0, beta0, Omega1, beta1, Omega2, beta2, omega3, beta3)\n",
-        "print(\"Your value is %3f: \"%(f[0,0]), \"True value of f: 0.498010\")"
+        "print(\"Your value is %3f: \"%(f[0,0]), \"True value of f: 0.310843\")"
       ],
       "metadata": {
         "id": "X7gYgOu6uIAt"
@@ -221,7 +221,7 @@
         "X_permuted = np.copy(X)\n",
         "\n",
         "f = graph_neural_network(A_permuted,X_permuted, Omega0, beta0, Omega1, beta1, Omega2, beta2, omega3, beta3)\n",
-        "print(\"Your value is %3f: \"%(f[0,0]), \"True value of f: 0.498010\")"
+        "print(\"Your value is %3f: \"%(f[0,0]), \"True value of f: 0.310843\")"
       ],
       "metadata": {
         "id": "F0zc3U_UuR5K"
@@ -241,4 +241,4 @@
       }
     }
   ]
-}
+}

Notebooks/Chap13/13_3_Neighborhood_Sampling.ipynb

@@ -268,7 +268,7 @@
       "source": [
         "# TODO Find the nodes in hidden layer 1 that connect to the nodes in hidden layer 2\n",
         "# using the adjacency matrix.  Then sample n_sample of these nodes randomly without\n",
-        "# replacement.  Make sure not to sample nodes that were already included in hidden layer 2 our the ouput layer.\n",
+        "# replacement.  Make sure not to sample nodes that were already included in hidden layer 2 our the output layer.\n",
         "# The nodes at hidden layer 1 are the union of these nodes and the nodes in hidden layer 2\n",
         "\n",
         "# Replace this line:\n",
@@ -311,4 +311,4 @@
       }
     }
   ]
-}
+}

Notebooks/Chap15/15_1_GAN_Toy_Example.ipynb

@@ -31,7 +31,7 @@
       "source": [
         "# **Notebook 15.1: GAN Toy example**\n",
         "\n",
-        "This notebook investigates the GAN toy example as illustred in figure 15.1 in the book.\n",
+        "This notebook investigates the GAN toy example as illustrated in figure 15.1 in the book.\n",
         "\n",
         "Work through the cells below, running each cell in turn. In various places you will see the words \"TO DO\". Follow the instructions at these places and make predictions about what is going to happen or write code to complete the functions.\n",
         "\n",
@@ -101,7 +101,7 @@
     {
       "cell_type": "markdown",
       "source": [
-        "Now, we define our disriminator.  This is a simple logistic regression model (1D linear model passed through sigmoid) that returns the probability that the data is real"
+        "Now, we define our discriminator.  This is a simple logistic regression model (1D linear model passed through sigmoid) that returns the probability that the data is real"
       ],
       "metadata": {
         "id": "Xrzd8aehYAYR"
@@ -387,7 +387,7 @@
         "print(\"Final parameters (phi0,phi1)\", phi0, phi1)\n",
         "for c_gan_iter in range(5):\n",
         "\n",
-        "  # Run generator to product syntehsized data\n",
+        "  # Run generator to product synthesized data\n",
         "  x_syn = generator(z, theta)\n",
         "  draw_data_model(x_real, x_syn, phi0, phi1)\n",
         "\n",

Notebooks/Chap15/15_2_Wasserstein_Distance.ipynb

@@ -29,9 +29,9 @@
     {
       "cell_type": "markdown",
       "source": [
-        "# **Notebook 15.2: Wassserstein Distance**\n",
+        "# **Notebook 15.2: Wasserstein Distance**\n",
         "\n",
-        "This notebook investigates the GAN toy example as illustred in figure 15.1 in the book.\n",
+        "This notebook investigates the GAN toy example as illustrated in figure 15.1 in the book.\n",
         "\n",
         "Work through the cells below, running each cell in turn. In various places you will see the words \"TO DO\". Follow the instructions at these places and make predictions about what is going to happen or write code to complete the functions.\n",
         "\n",

Notebooks/Chap16/16_2_Autoregressive_Flows.ipynb

@@ -65,7 +65,7 @@
     {
       "cell_type": "code",
       "source": [
-        "# First let's make the 1D piecewise linear mapping as illustated in figure 16.5\n",
+        "# First let's make the 1D piecewise linear mapping as illustrated in figure 16.5\n",
         "def g(h, phi):\n",
         "  # TODO -- write this function (equation 16.12)\n",
         "  # Note: If you have the first printing of the book, there is a mistake in equation 16.12\n",
@@ -156,7 +156,7 @@
     {
       "cell_type": "markdown",
       "source": [
-        "Now let's define an autogressive flow.  Let's switch to looking at figure 16.7.# We'll assume that our piecewise function will use five parameters phi1,phi2,phi3,phi4,phi5"
+        "Now let's define an autoregressive flow.  Let's switch to looking at figure 16.7.# We'll assume that our piecewise function will use five parameters phi1,phi2,phi3,phi4,phi5"
       ],
       "metadata": {
         "id": "t8XPxipfd7hz"
@@ -175,7 +175,7 @@
         "  x = x/ np.sum(x) ;\n",
         "  return x\n",
         "\n",
-        "# Return value of phi that doesn't depend on any of the iputs\n",
+        "# Return value of phi that doesn't depend on any of the inputs\n",
         "def get_phi():\n",
         "  return np.array([0.2, 0.1, 0.4, 0.05, 0.25])\n",
         "\n",

Notebooks/Chap16/16_3_Contraction_Mappings.ipynb

@@ -1,33 +1,22 @@
 {
-  "nbformat": 4,
-  "nbformat_minor": 0,
-  "metadata": {
-    "colab": {
-      "provenance": [],
-      "authorship_tag": "ABX9TyNeCWINUqqUGKMcxsqPFTAh",
-      "include_colab_link": true
-    },
-    "kernelspec": {
-      "name": "python3",
-      "display_name": "Python 3"
-    },
-    "language_info": {
-      "name": "python"
-    }
-  },
   "cells": [
     {
+      "attachments": {},
       "cell_type": "markdown",
       "metadata": {
-        "id": "view-in-github",
+        "colab_type": "text",
-        "colab_type": "text"
+        "id": "view-in-github"
       },
       "source": [
         "<a href=\"https://colab.research.google.com/github/udlbook/udlbook/blob/main/Notebooks/Chap16/16_3_Contraction_Mappings.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
       ]
     },
     {
+      "attachments": {},
       "cell_type": "markdown",
+      "metadata": {
+        "id": "t9vk9Elugvmi"
+      },
       "source": [
         "# **Notebook 16.3: Contraction mappings**\n",
         "\n",
@@ -36,38 +25,40 @@
         "Work through the cells below, running each cell in turn. In various places you will see the words \"TO DO\". Follow the instructions at these places and make predictions about what is going to happen or write code to complete the functions.\n",
         "\n",
         "Contact me at udlbookmail@gmail.com if you find any mistakes or have any suggestions."
-      ],
+      ]
-      "metadata": {
-        "id": "t9vk9Elugvmi"
-      }
     },
     {
       "cell_type": "code",
-      "source": [
+      "execution_count": null,
-        "import numpy as np\n",
-        "import matplotlib.pyplot as plt"
-      ],
       "metadata": {
         "id": "OLComQyvCIJ7"
       },
-      "execution_count": null,
+      "outputs": [],
-      "outputs": []
+      "source": [
+        "import numpy as np\n",
+        "import matplotlib.pyplot as plt"
+      ]
     },
     {
       "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "4Pfz2KSghdVI"
+      },
+      "outputs": [],
       "source": [
         "# Define a function that is a contraction mapping\n",
         "def f(z):\n",
         "    return 0.3 + 0.5 *z + 0.02 * np.sin(z*15)"
-      ],
+      ]
-      "metadata": {
-        "id": "4Pfz2KSghdVI"
-      },
-      "execution_count": null,
-      "outputs": []
     },
     {
       "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "zEwCbIx0hpAI"
+      },
+      "outputs": [],
       "source": [
         "def draw_function(f, fixed_point=None):\n",
         "  z = np.arange(0,1,0.01)\n",
@@ -84,35 +75,36 @@
         "  ax.set_xlabel('Input, $z$')\n",
         "  ax.set_ylabel('Output, f$[z]$')\n",
         "  plt.show()"
-      ],
+      ]
-      "metadata": {
-        "id": "zEwCbIx0hpAI"
-      },
-      "execution_count": null,
-      "outputs": []
     },
     {
       "cell_type": "code",
-      "source": [
+      "execution_count": null,
-        "draw_function(f)"
-      ],
       "metadata": {
         "id": "k4e5Yu0fl8bz"
       },
-      "execution_count": null,
+      "outputs": [],
-      "outputs": []
+      "source": [
+        "draw_function(f)"
+      ]
     },
     {
+      "attachments": {},
       "cell_type": "markdown",
-      "source": [
-        "Now let's find where $\\mbox{f}[z]=z$ using fixed point iteration"
-      ],
       "metadata": {
         "id": "DfgKrpCAjnol"
-      }
+      },
+      "source": [
+        "Now let's find where $\\text{f}[z]=z$ using fixed point iteration"
+      ]
     },
     {
       "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "bAOBvZT-j3lv"
+      },
+      "outputs": [],
       "source": [
         "# Takes a function f and a starting point z\n",
         "def fixed_point_iteration(f, z0):\n",
@@ -125,115 +117,117 @@
         "\n",
         "\n",
         "  return z_out"
-      ],
+      ]
-      "metadata": {
-        "id": "bAOBvZT-j3lv"
-      },
-      "execution_count": null,
-      "outputs": []
     },
     {
+      "attachments": {},
       "cell_type": "markdown",
-      "source": [
-        "Now let's test that and plot the solution"
-      ],
       "metadata": {
         "id": "CAS0lgIomAa0"
-      }
+      },
+      "source": [
+        "Now let's test that and plot the solution"
+      ]
     },
     {
       "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "EYQZJdNPk8Lg"
+      },
+      "outputs": [],
       "source": [
         "# Now let's test that\n",
         "z = fixed_point_iteration(f, 0.2)\n",
         "draw_function(f, z)"
-      ],
+      ]
-      "metadata": {
-        "id": "EYQZJdNPk8Lg"
-      },
-      "execution_count": null,
-      "outputs": []
     },
     {
       "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "4DipPiqVlnwJ"
+      },
+      "outputs": [],
       "source": [
         "# Let's define another function\n",
         "def f2(z):\n",
         "    return 0.7 + -0.6 *z + 0.03 * np.sin(z*15)\n",
         "draw_function(f2)"
-      ],
+      ]
-      "metadata": {
-        "id": "4DipPiqVlnwJ"
-      },
-      "execution_count": null,
-      "outputs": []
     },
     {
       "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "tYOdbWcomdEE"
+      },
+      "outputs": [],
       "source": [
         "# Now let's test that\n",
         "# TODO Before running this code, predict what you think will happen\n",
         "z = fixed_point_iteration(f2, 0.9)\n",
         "draw_function(f2, z)"
-      ],
+      ]
-      "metadata": {
-        "id": "tYOdbWcomdEE"
-      },
-      "execution_count": null,
-      "outputs": []
     },
     {
       "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "Mni37RUpmrIu"
+      },
+      "outputs": [],
       "source": [
         "# Let's define another function\n",
         "# Define a function that is a contraction mapping\n",
         "def f3(z):\n",
         "    return -0.2 + 1.5 *z + 0.1 * np.sin(z*15)\n",
         "draw_function(f3)"
-      ],
+      ]
-      "metadata": {
-        "id": "Mni37RUpmrIu"
-      },
-      "execution_count": null,
-      "outputs": []
     },
     {
       "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "agt5mfJrnM1O"
+      },
+      "outputs": [],
       "source": [
         "# Now let's test that\n",
         "# TODO Before running this code, predict what you think will happen\n",
         "z = fixed_point_iteration(f3, 0.7)\n",
         "draw_function(f3, z)"
-      ],
+      ]
-      "metadata": {
-        "id": "agt5mfJrnM1O"
-      },
-      "execution_count": null,
-      "outputs": []
     },
     {
+      "attachments": {},
       "cell_type": "markdown",
-      "source": [
-        "Finally, let's invert a problem of the form $y = z+ f[z]$  for a given value of $y$. What is the $z$ that maps to it?"
-      ],
       "metadata": {
         "id": "n6GI46-ZoQz6"
-      }
+      },
+      "source": [
+        "Finally, let's invert a problem of the form $y = z+ f[z]$  for a given value of $y$. What is the $z$ that maps to it?"
+      ]
     },
     {
       "cell_type": "code",
-      "source": [
+      "execution_count": null,
-        "def f4(z):\n",
-        "   return -0.3 + 0.5 *z + 0.02 * np.sin(z*15)"
-      ],
       "metadata": {
         "id": "dy6r3jr9rjPf"
       },
-      "execution_count": null,
+      "outputs": [],
-      "outputs": []
+      "source": [
+        "def f4(z):\n",
+        "   return -0.3 + 0.5 *z + 0.02 * np.sin(z*15)"
+      ]
     },
     {
       "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "GMX64Iz0nl-B"
+      },
+      "outputs": [],
       "source": [
         "def fixed_point_iteration_z_plus_f(f, y, z0):\n",
         "  # TODO -- write this function\n",
@@ -241,15 +235,15 @@
         "  z_out = 1\n",
         "\n",
         "  return z_out"
-      ],
+      ]
-      "metadata": {
-        "id": "GMX64Iz0nl-B"
-      },
-      "execution_count": null,
-      "outputs": []
     },
     {
       "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "uXxKHad5qT8Y"
+      },
+      "outputs": [],
       "source": [
         "def draw_function2(f, y, fixed_point=None):\n",
         "  z = np.arange(0,1,0.01)\n",
@@ -267,15 +261,15 @@
         "  ax.set_xlabel('Input, $z$')\n",
         "  ax.set_ylabel('Output, z+f$[z]$')\n",
         "  plt.show()"
-      ],
+      ]
-      "metadata": {
-        "id": "uXxKHad5qT8Y"
-      },
-      "execution_count": null,
-      "outputs": []
     },
     {
       "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "mNEBXC3Aqd_1"
+      },
+      "outputs": [],
       "source": [
         "# Test this out and draw\n",
         "y = 0.8\n",
@@ -283,12 +277,23 @@
         "draw_function2(f4,y,z)\n",
         "# If you have done this correctly, the red dot should be\n",
         "# where the cyan curve has a y value of 0.8"
-      ],
+      ]
-      "metadata": {
-        "id": "mNEBXC3Aqd_1"
-      },
-      "execution_count": null,
-      "outputs": []
     }
-  ]
+  ],
-}
+  "metadata": {
+    "colab": {
+      "authorship_tag": "ABX9TyNeCWINUqqUGKMcxsqPFTAh",
+      "include_colab_link": true,
+      "provenance": []
+    },
+    "kernelspec": {
+      "display_name": "Python 3",
+      "name": "python3"
+    },
+    "language_info": {
+      "name": "python"
+    }
+  },
+  "nbformat": 4,
+  "nbformat_minor": 0
+}

Notebooks/Chap17/17_1_Latent_Variable_Models.ipynb

@@ -1,33 +1,22 @@
 {
-  "nbformat": 4,
-  "nbformat_minor": 0,
-  "metadata": {
-    "colab": {
-      "provenance": [],
-      "authorship_tag": "ABX9TyMBYNsjj1iTgHUYhAXqUYJd",
-      "include_colab_link": true
-    },
-    "kernelspec": {
-      "name": "python3",
-      "display_name": "Python 3"
-    },
-    "language_info": {
-      "name": "python"
-    }
-  },
   "cells": [
     {
+      "attachments": {},
       "cell_type": "markdown",
       "metadata": {
-        "id": "view-in-github",
+        "colab_type": "text",
-        "colab_type": "text"
+        "id": "view-in-github"
       },
       "source": [
         "<a href=\"https://colab.research.google.com/github/udlbook/udlbook/blob/main/Notebooks/Chap17/17_1_Latent_Variable_Models.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
       ]
     },
     {
+      "attachments": {},
       "cell_type": "markdown",
+      "metadata": {
+        "id": "t9vk9Elugvmi"
+      },
       "source": [
         "# **Notebook 17.1: Latent variable models**\n",
         "\n",
@@ -36,72 +25,76 @@
         "Work through the cells below, running each cell in turn. In various places you will see the words \"TO DO\". Follow the instructions at these places and make predictions about what is going to happen or write code to complete the functions.\n",
         "\n",
         "Contact me at udlbookmail@gmail.com if you find any mistakes or have any suggestions."
-      ],
+      ]
-      "metadata": {
-        "id": "t9vk9Elugvmi"
-      }
     },
     {
       "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "OLComQyvCIJ7"
+      },
+      "outputs": [],
       "source": [
         "import numpy as np\n",
         "import matplotlib.pyplot as plt\n",
         "import scipy\n",
         "from matplotlib.colors import ListedColormap\n",
         "from matplotlib import cm"
-      ],
+      ]
-      "metadata": {
-        "id": "OLComQyvCIJ7"
-      },
-      "execution_count": null,
-      "outputs": []
     },
     {
+      "attachments": {},
       "cell_type": "markdown",
+      "metadata": {
+        "id": "IyVn-Gi-p7wf"
+      },
       "source": [
         "We'll assume that our base distribution over the latent variables is a 1D standard normal so that\n",
         "\n",
         "\\begin{equation}\n",
-        "Pr(z) = \\mbox{Norm}_{z}[0,1]\n",
+        "Pr(z) = \\text{Norm}_{z}[0,1]\n",
         "\\end{equation}\n",
         "\n",
         "As in figure 17.2, we'll assume that the output is two dimensional, we we need to define a function that maps from the 1D latent variable to two dimensions.  Usually, we would use a neural network, but in this case, we'll just define an arbitrary relationship.\n",
         "\n",
-        "\\begin{eqnarray}\n",
+        "\\begin{align}\n",
         "x_{1} &=& 0.5\\cdot\\exp\\Bigl[\\sin\\bigl[2+ 3.675 z \\bigr]\\Bigr]\\\\\n",
         "x_{2} &=& \\sin\\bigl[2+ 2.85 z \\bigr]\n",
-        "\\end{eqnarray}"
+        "\\end{align}"
-      ],
+      ]
-      "metadata": {
-        "id": "IyVn-Gi-p7wf"
-      }
     },
     {
       "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "ZIfQwhd-AV6L"
+      },
+      "outputs": [],
       "source": [
         "# The function that maps z to x1 and x2\n",
         "def f(z):\n",
         "  x_1 = np.exp(np.sin(2+z*3.675)) * 0.5\n",
         "  x_2 = np.cos(2+z*2.85)\n",
         "  return x_1, x_2"
-      ],
+      ]
-      "metadata": {
-        "id": "ZIfQwhd-AV6L"
-      },
-      "execution_count": null,
-      "outputs": []
     },
     {
+      "attachments": {},
       "cell_type": "markdown",
-      "source": [
-        "Let's plot the 3D relation between the two observed variables $x_{1}$ and $x_{2}$ and the latent variables $z$ as in figure 17.2 of the book.  We'll use the opacity to represent the prior probability $Pr(z)$."
-      ],
       "metadata": {
         "id": "KB9FU34onW1j"
-      }
+      },
+      "source": [
+        "Let's plot the 3D relation between the two observed variables $x_{1}$ and $x_{2}$ and the latent variables $z$ as in figure 17.2 of the book.  We'll use the opacity to represent the prior probability $Pr(z)$."
+      ]
     },
     {
       "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "lW08xqAgnP4q"
+      },
+      "outputs": [],
       "source": [
         "def draw_3d_projection(z,pr_z, x1,x2):\n",
         "  alpha = pr_z / np.max(pr_z)\n",
@@ -118,28 +111,28 @@
         "  ax.set_zlim(-1,1)\n",
         "  ax.set_box_aspect((3,1,1))\n",
         "  plt.show()"
-      ],
+      ]
-      "metadata": {
-        "id": "lW08xqAgnP4q"
-      },
-      "execution_count": null,
-      "outputs": []
     },
     {
       "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "9DUTauMi6tPk"
+      },
+      "outputs": [],
       "source": [
         "# Compute the prior\n",
         "def get_prior(z):\n",
         "  return scipy.stats.multivariate_normal.pdf(z)"
-      ],
+      ]
-      "metadata": {
-        "id": "9DUTauMi6tPk"
-      },
-      "execution_count": null,
-      "outputs": []
     },
     {
       "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "PAzHq461VqvF"
+      },
+      "outputs": [],
       "source": [
         "# Define the latent variable values\n",
         "z = np.arange(-3.0,3.0,0.01)\n",
@@ -149,40 +142,41 @@
         "x1,x2 = f(z)\n",
         "# Plot the function\n",
         "draw_3d_projection(z,pr_z, x1,x2)"
-      ],
+      ]
-      "metadata": {
-        "id": "PAzHq461VqvF"
-      },
-      "execution_count": null,
-      "outputs": []
     },
     {
+      "attachments": {},
       "cell_type": "markdown",
-      "source": [
-        "The likelihood is defined as:\n",
-        "\\begin{eqnarray}\n",
-        " Pr(x_1,x_2|z) &=&  \\mbox{Norm}_{[x_1,x_2]}\\Bigl[\\mathbf{f}[z],\\sigma^{2}\\mathbf{I}\\Bigr]\n",
-        "\\end{eqnarray}\n",
-        "\n",
-        "so we will also need to define the noise level $\\sigma^2$"
-      ],
       "metadata": {
         "id": "sQg2gKR5zMrF"
-      }
+      },
+      "source": [
+        "The likelihood is defined as:\n",
+        "\\begin{align}\n",
+        " Pr(x_1,x_2|z) &=&  \\text{Norm}_{[x_1,x_2]}\\Bigl[\\mathbf{f}[z],\\sigma^{2}\\mathbf{I}\\Bigr]\n",
+        "\\end{align}\n",
+        "\n",
+        "so we will also need to define the noise level $\\sigma^2$"
+      ]
     },
     {
       "cell_type": "code",
-      "source": [
+      "execution_count": null,
-        "sigma_sq = 0.04"
-      ],
       "metadata": {
         "id": "In_Vg4_0nva3"
       },
-      "execution_count": null,
+      "outputs": [],
-      "outputs": []
+      "source": [
+        "sigma_sq = 0.04"
+      ]
     },
     {
       "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "6P6d-AgAqxXZ"
+      },
+      "outputs": [],
       "source": [
         "# Draws a heatmap to represent a probability distribution, possibly with samples overlaed\n",
         "def plot_heatmap(x1_mesh,x2_mesh,y_mesh, x1_samples=None, x2_samples=None, title=None):\n",
@@ -207,15 +201,15 @@
         "  ax.set_xlabel('$x_1$'); ax.set_ylabel('$x_2$')\n",
         "  plt.show()\n",
         "\n"
-      ],
+      ]
-      "metadata": {
-        "id": "6P6d-AgAqxXZ"
-      },
-      "execution_count": null,
-      "outputs": []
     },
     {
       "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "diYKb7_ZgjlJ"
+      },
+      "outputs": [],
       "source": [
         "# Returns the likelihood\n",
         "def get_likelihood(x1_mesh, x2_mesh, z_val):\n",
@@ -226,24 +220,25 @@
         "  mn = scipy.stats.multivariate_normal([x1, x2], [[sigma_sq, 0], [0, sigma_sq]])\n",
         "  pr_x1_x2_given_z_val = mn.pdf(np.dstack((x1_mesh, x2_mesh)))\n",
         "  return pr_x1_x2_given_z_val"
-      ],
+      ]
-      "metadata": {
-        "id": "diYKb7_ZgjlJ"
-      },
-      "execution_count": null,
-      "outputs": []
     },
     {
+      "attachments": {},
       "cell_type": "markdown",
-      "source": [
-        "Now let's plot the likelihood $Pr(x_1,x_2|z)$ as in fig 17.3b in the book."
-      ],
       "metadata": {
         "id": "0X4NwixzqxtZ"
-      }
+      },
+      "source": [
+        "Now let's plot the likelihood $Pr(x_1,x_2|z)$ as in fig 17.3b in the book."
+      ]
     },
     {
       "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "hWfqK-Oz5_DT"
+      },
+      "outputs": [],
       "source": [
         "# Choose some z value\n",
         "z_val = 1.8\n",
@@ -253,33 +248,34 @@
         "pr_x1_x2_given_z_val = get_likelihood(x1_mesh,x2_mesh, z_val)\n",
         "\n",
         "# Plot the result\n",
-        "plot_heatmap(x1_mesh, x2_mesh, pr_x1_x2_given_z_val, title=\"Conditional distribution $Pr(x1,x2|z)$\")\n",
+        "plot_heatmap(x1_mesh, x2_mesh, pr_x1_x2_given_z_val, title=\"Conditional distribution $Pr(x_1,x_2|z)$\")\n",
         "\n",
         "# TODO -- Experiment with different values of z and make sure that you understand the what is happening."
-      ],
+      ]
-      "metadata": {
-        "id": "hWfqK-Oz5_DT"
-      },
-      "execution_count": null,
-      "outputs": []
     },
     {
+      "attachments": {},
       "cell_type": "markdown",
+      "metadata": {
+        "id": "25xqXnmFo-PH"
+      },
       "source": [
         "The data density is found by marginalizing over the latent variables $z$:\n",
         "\n",
-        "\\begin{eqnarray}\n",
+        "\\begin{align}\n",
         " Pr(x_1,x_2) &=& \\int Pr(x_1,x_2, z) dz \\nonumber \\\\\n",
         " &=& \\int Pr(x_1,x_2 | z) \\cdot Pr(z)dz\\nonumber \\\\\n",
-        " &=& \\int \\mbox{Norm}_{[x_1,x_2]}\\Bigl[\\mathbf{f}[z],\\sigma^{2}\\mathbf{I}\\Bigr]\\cdot \\mbox{Norm}_{z}\\left[\\mathbf{0},\\mathbf{I}\\right]dz.\n",
+        " &=& \\int \\text{Norm}_{[x_1,x_2]}\\Bigl[\\mathbf{f}[z],\\sigma^{2}\\mathbf{I}\\Bigr]\\cdot \\text{Norm}_{z}\\left[\\mathbf{0},\\mathbf{I}\\right]dz.\n",
-        "\\end{eqnarray}"
+        "\\end{align}"
-      ],
+      ]
-      "metadata": {
-        "id": "25xqXnmFo-PH"
-      }
     },
     {
       "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "H0Ijce9VzeCO"
+      },
+      "outputs": [],
       "source": [
         "# TODO Compute the data density\n",
         "# We can't integrate this function in closed form\n",
@@ -292,25 +288,26 @@
         "\n",
         "\n",
         "# Plot the result\n",
-        "plot_heatmap(x1_mesh, x2_mesh, pr_x1_x2, title=\"Data density $Pr(x1,x2)$\")\n"
+        "plot_heatmap(x1_mesh, x2_mesh, pr_x1_x2, title=\"Data density $Pr(x_1,x_2)$\")\n"
-      ],
+      ]
-      "metadata": {
-        "id": "H0Ijce9VzeCO"
-      },
-      "execution_count": null,
-      "outputs": []
     },
     {
+      "attachments": {},
       "cell_type": "markdown",
-      "source": [
-        "Now let's draw some samples from the model"
-      ],
       "metadata": {
         "id": "W264N7By_h9y"
-      }
+      },
+      "source": [
+        "Now let's draw some samples from the model"
+      ]
     },
     {
       "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "Li3mK_I48k0k"
+      },
+      "outputs": [],
       "source": [
         "def draw_samples(n_sample):\n",
         "  # TODO Write this routine to draw n_sample samples from the model\n",
@@ -320,37 +317,38 @@
         "  x1_samples=0; x2_samples = 0;\n",
         "\n",
         "  return x1_samples, x2_samples"
-      ],
+      ]
-      "metadata": {
-        "id": "Li3mK_I48k0k"
-      },
-      "execution_count": null,
-      "outputs": []
     },
     {
+      "attachments": {},
       "cell_type": "markdown",
-      "source": [
-        "Let's plot those samples on top of the heat map."
-      ],
       "metadata": {
         "id": "D7N7oqLe-eJO"
-      }
+      },
+      "source": [
+        "Let's plot those samples on top of the heat map."
+      ]
     },
     {
       "cell_type": "code",
-      "source": [
+      "execution_count": null,
-        "x1_samples, x2_samples = draw_samples(500)\n",
-        "# Plot the result\n",
-        "plot_heatmap(x1_mesh, x2_mesh, pr_x1_x2, x1_samples, x2_samples, title=\"Data density $Pr(x1,x2)$\")\n"
-      ],
       "metadata": {
         "id": "XRmWv99B-BWO"
       },
-      "execution_count": null,
+      "outputs": [],
-      "outputs": []
+      "source": [
+        "x1_samples, x2_samples = draw_samples(500)\n",
+        "# Plot the result\n",
+        "plot_heatmap(x1_mesh, x2_mesh, pr_x1_x2, x1_samples, x2_samples, title=\"Data density $Pr(x_1,x_2)$\")\n"
+      ]
     },
     {
       "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "PwOjzPD5_1OF"
+      },
+      "outputs": [],
       "source": [
         "# Return the posterior distribution\n",
         "def get_posterior(x1,x2):\n",
@@ -364,15 +362,15 @@
         "\n",
         "\n",
         "  return z, pr_z_given_x1_x2"
-      ],
+      ]
-      "metadata": {
-        "id": "PwOjzPD5_1OF"
-      },
-      "execution_count": null,
-      "outputs": []
     },
     {
       "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "PKFUY42K-Tp7"
+      },
+      "outputs": [],
       "source": [
         "x1 = 0.9; x2 = -0.9\n",
         "z, pr_z_given_x1_x2 = get_posterior(x1,x2)\n",
@@ -385,12 +383,23 @@
         "ax.set_xlim([-3,3])\n",
         "ax.set_ylim([0,1.5 * np.max(pr_z_given_x1_x2)])\n",
         "plt.show()"
-      ],
+      ]
-      "metadata": {
-        "id": "PKFUY42K-Tp7"
-      },
-      "execution_count": null,
-      "outputs": []
     }
-  ]
+  ],
-}
+  "metadata": {
+    "colab": {
+      "authorship_tag": "ABX9TyOSEQVqxE5KrXmsZVh9M3gq",
+      "include_colab_link": true,
+      "provenance": []
+    },
+    "kernelspec": {
+      "display_name": "Python 3",
+      "name": "python3"
+    },
+    "language_info": {
+      "name": "python"
+    }
+  },
+  "nbformat": 4,
+  "nbformat_minor": 0
+}

Notebooks/Chap17/17_2_Reparameterization_Trick.ipynb

@@ -1,33 +1,22 @@
 {
-  "nbformat": 4,
-  "nbformat_minor": 0,
-  "metadata": {
-    "colab": {
-      "provenance": [],
-      "authorship_tag": "ABX9TyOxO2/0DTH4n4zhC97qbagY",
-      "include_colab_link": true
-    },
-    "kernelspec": {
-      "name": "python3",
-      "display_name": "Python 3"
-    },
-    "language_info": {
-      "name": "python"
-    }
-  },
   "cells": [
     {
+      "attachments": {},
       "cell_type": "markdown",
       "metadata": {
-        "id": "view-in-github",
+        "colab_type": "text",
-        "colab_type": "text"
+        "id": "view-in-github"
       },
       "source": [
         "<a href=\"https://colab.research.google.com/github/udlbook/udlbook/blob/main/Notebooks/Chap17/17_2_Reparameterization_Trick.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
       ]
     },
     {
+      "attachments": {},
       "cell_type": "markdown",
+      "metadata": {
+        "id": "t9vk9Elugvmi"
+      },
       "source": [
         "# **Notebook 17.2: Reparameterization trick**\n",
         "\n",
@@ -36,30 +25,31 @@
         "Work through the cells below, running each cell in turn. In various places you will see the words \"TO DO\". Follow the instructions at these places and make predictions about what is going to happen or write code to complete the functions.\n",
         "\n",
         "Contact me at udlbookmail@gmail.com if you find any mistakes or have any suggestions."
-      ],
+      ]
-      "metadata": {
-        "id": "t9vk9Elugvmi"
-      }
     },
     {
       "cell_type": "code",
-      "source": [
+      "execution_count": null,
-        "import numpy as np\n",
-        "import matplotlib.pyplot as plt"
-      ],
       "metadata": {
         "id": "OLComQyvCIJ7"
       },
-      "execution_count": null,
+      "outputs": [],
-      "outputs": []
+      "source": [
+        "import numpy as np\n",
+        "import matplotlib.pyplot as plt"
+      ]
     },
     {
+      "attachments": {},
       "cell_type": "markdown",
+      "metadata": {
+        "id": "paLz5RukZP1J"
+      },
       "source": [
-        "The reparameterization trick computes the derivative of an expectation of a function $\\mbox{f}[x]$:\n",
+        "The reparameterization trick computes the derivative of an expectation of a function $\\text{f}[x]$:\n",
         "\n",
         "\\begin{equation}\n",
-        "\\frac{\\partial}{\\partial \\boldsymbol\\phi} \\mathbb{E}_{Pr(x|\\boldsymbol\\phi)}\\bigl[\\mbox{f}[x]\\bigr],\n",
+        "\\frac{\\partial}{\\partial \\boldsymbol\\phi} \\mathbb{E}_{Pr(x|\\boldsymbol\\phi)}\\bigl[\\text{f}[x]\\bigr],\n",
         "\\end{equation}\n",
         "\n",
         "with respect to the parameters $\\boldsymbol\\phi$ of the distribution $Pr(x|\\boldsymbol\\phi)$ that the expectation is over.\n",
@@ -67,23 +57,25 @@
         "Let's consider a simple concrete example, where:\n",
         "\n",
         "\\begin{equation}\n",
-        "Pr(x|\\phi) = \\mbox{Norm}_{x}\\Bigl[\\mu, \\sigma^2\\Bigr]=\\mbox{Norm}_{x}\\Bigl[\\phi^3,(\\exp[\\phi])^2\\Bigr]\n",
+        "Pr(x|\\phi) = \\text{Norm}_{x}\\Bigl[\\mu, \\sigma^2\\Bigr]=\\text{Norm}_{x}\\Bigl[\\phi^3,(\\exp[\\phi])^2\\Bigr]\n",
         "\\end{equation}\n",
         "\n",
         "and\n",
         "\n",
         "\\begin{equation}\n",
-        "\\mbox{f}[x] = x^2+\\sin[x]\n",
+        "\\text{f}[x] = x^2+\\sin[x]\n",
         "\\end{equation}"
-      ],
+      ]
-      "metadata": {
-        "id": "paLz5RukZP1J"
-      }
     },
     {
       "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "FdEbMnDBY0i9"
+      },
+      "outputs": [],
       "source": [
-        "# Let's approximate this expecctation for a particular value of phi\n",
+        "# Let's approximate this expectation for a particular value of phi\n",
         "def compute_expectation(phi, n_samples):\n",
         "  # TODO complete this function\n",
         "  # 1. Compute the mean of the normal distribution, mu\n",
@@ -96,15 +88,15 @@
         "\n",
         "\n",
         "  return expected_f_given_phi"
-      ],
+      ]
-      "metadata": {
-        "id": "FdEbMnDBY0i9"
-      },
-      "execution_count": null,
-      "outputs": []
     },
     {
       "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "FTh7LJ0llNJZ"
+      },
+      "outputs": [],
       "source": [
         "# Set the seed so the random numbers are all the same\n",
         "np.random.seed(0)\n",
@@ -119,24 +111,25 @@
         "n_samples = 10000000\n",
         "expected_f_given_phi2 = compute_expectation(phi2, n_samples)\n",
         "print(\"Your value: \", expected_f_given_phi2, \", True value:  0.8176793102849222\")"
-      ],
+      ]
-      "metadata": {
-        "id": "FTh7LJ0llNJZ"
-      },
-      "execution_count": null,
-      "outputs": []
     },
     {
+      "attachments": {},
       "cell_type": "markdown",
-      "source": [
-        "Le't plot this expectation as a function of phi"
-      ],
       "metadata": {
         "id": "r5Hl2QkimWx9"
-      }
+      },
+      "source": [
+        "Le't plot this expectation as a function of phi"
+      ]
     },
     {
       "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "05XxVLJxmkER"
+      },
+      "outputs": [],
       "source": [
         "phi_vals = np.arange(-1.5,1.5, 0.05)\n",
         "expected_vals = np.zeros_like(phi_vals)\n",
@@ -149,15 +142,14 @@
         "ax.set_xlabel('Parameter $\\phi$')\n",
         "ax.set_ylabel('$\\mathbb{E}_{Pr(x|\\phi)}[f[x]]$')\n",
         "plt.show()"
-      ],
+      ]
-      "metadata": {
-        "id": "05XxVLJxmkER"
-      },
-      "execution_count": null,
-      "outputs": []
     },
     {
+      "attachments": {},
       "cell_type": "markdown",
+      "metadata": {
+        "id": "zTCykVeWqj_O"
+      },
       "source": [
         "It's this curve that we want to find the derivative of (so for example, we could run gradient descent and find the minimum.\n",
         "\n",
@@ -166,28 +158,30 @@
         "The answer is the reparameterization trick.  We note that:\n",
         "\n",
         "\\begin{equation}\n",
-        "\\mbox{Norm}_{x}\\Bigl[\\mu, \\sigma^2\\Bigr]=\\mbox{Norm}_{x}\\Bigl[0, 1\\Bigr] \\times \\sigma + \\mu\n",
+        "\\text{Norm}_{x}\\Bigl[\\mu, \\sigma^2\\Bigr]=\\text{Norm}_{x}\\Bigl[0, 1\\Bigr] \\times \\sigma + \\mu\n",
         "\\end{equation}\n",
         "\n",
         "and so:\n",
         "\n",
         "\\begin{equation}\n",
-        "\\mbox{Norm}_{x}\\Bigl[\\phi^3,(\\exp[\\phi])^2\\Bigr]  = \\mbox{Norm}_{x}\\Bigl[0, 1\\Bigr] \\times \\exp[\\phi]+ \\phi^3\n",
+        "\\text{Norm}_{x}\\Bigl[\\phi^3,(\\exp[\\phi])^2\\Bigr]  = \\text{Norm}_{x}\\Bigl[0, 1\\Bigr] \\times \\exp[\\phi]+ \\phi^3\n",
         "\\end{equation}\n",
         "\n",
-        "So, if we draw a sample $\\epsilon^*$ from $\\mbox{Norm}_{\\epsilon}[0, 1]$, then we can compute a sample $x^*$ as:\n",
+        "So, if we draw a sample $\\epsilon^*$ from $\\text{Norm}_{\\epsilon}[0, 1]$, then we can compute a sample $x^*$ as:\n",
         "\n",
-        "\\begin{eqnarray*}\n",
+        "\\begin{align}\n",
         "x^* &=& \\epsilon^* \\times \\sigma + \\mu \\\\\n",
         "&=& \\epsilon^* \\times \\exp[\\phi]+ \\phi^3\n",
-        "\\end{eqnarray*}"
+        "\\end{align}"
-      ],
+      ]
-      "metadata": {
-        "id": "zTCykVeWqj_O"
-      }
     },
     {
       "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "w13HVpi9q8nF"
+      },
+      "outputs": [],
       "source": [
         "def compute_df_dx_star(x_star):\n",
         "  # TODO Compute this derivative (function defined at the top)\n",
@@ -222,15 +216,15 @@
         "\n",
         "\n",
         "  return df_dphi"
-      ],
+      ]
-      "metadata": {
-        "id": "w13HVpi9q8nF"
-      },
-      "execution_count": null,
-      "outputs": []
     },
     {
       "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "ntQT4An79kAl"
+      },
+      "outputs": [],
       "source": [
         "# Set the seed so the random numbers are all the same\n",
         "np.random.seed(0)\n",
@@ -241,15 +235,15 @@
         "\n",
         "deriv = compute_derivative_of_expectation(phi1, n_samples)\n",
         "print(\"Your value: \", deriv, \", True value:  5.726338035051403\")"
-      ],
+      ]
-      "metadata": {
-        "id": "ntQT4An79kAl"
-      },
-      "execution_count": null,
-      "outputs": []
     },
     {
       "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "t0Jqd_IN_lMU"
+      },
+      "outputs": [],
       "source": [
         "phi_vals = np.arange(-1.5,1.5, 0.05)\n",
         "deriv_vals = np.zeros_like(phi_vals)\n",
@@ -262,37 +256,37 @@
         "ax.set_xlabel('Parameter $\\phi$')\n",
         "ax.set_ylabel('$\\partial/\\partial\\phi\\mathbb{E}_{Pr(x|\\phi)}[f[x]]$')\n",
         "plt.show()"
-      ],
+      ]
-      "metadata": {
-        "id": "t0Jqd_IN_lMU"
-      },
-      "execution_count": null,
-      "outputs": []
     },
     {
+      "attachments": {},
       "cell_type": "markdown",
-      "source": [
-        "This should look plausibly like the derivative of the function we plotted above!"
-      ],
       "metadata": {
         "id": "ASu4yKSwAEYI"
-      }
+      },
+      "source": [
+        "This should look plausibly like the derivative of the function we plotted above!"
+      ]
     },
     {
+      "attachments": {},
       "cell_type": "markdown",
+      "metadata": {
+        "id": "xoFR1wifc8-b"
+      },
       "source": [
-        "The reparameterization trick computes the derivative of an expectation of a function $\\mbox{f}[x]$:\n",
+        "The reparameterization trick computes the derivative of an expectation of a function $\\text{f}[x]$:\n",
         "\n",
         "\\begin{equation}\n",
-        "\\frac{\\partial}{\\partial \\boldsymbol\\phi} \\mathbb{E}_{Pr(x|\\boldsymbol\\phi)}\\bigl[\\mbox{f}[x]\\bigr],\n",
+        "\\frac{\\partial}{\\partial \\boldsymbol\\phi} \\mathbb{E}_{Pr(x|\\boldsymbol\\phi)}\\bigl[\\text{f}[x]\\bigr],\n",
         "\\end{equation}\n",
         "\n",
         "with respect to the parameters $\\boldsymbol\\phi$ of the distribution $Pr(x|\\boldsymbol\\phi)$ that the expectation is over. This derivative can also be computed as:\n",
         "\n",
-        "\\begin{eqnarray}\n",
+        "\\begin{align}\n",
-        "\\frac{\\partial}{\\partial \\boldsymbol\\phi} \\mathbb{E}_{Pr(x|\\boldsymbol\\phi)}\\bigl[\\mbox{f}[x]\\bigr] &=& \\mathbb{E}_{Pr(x|\\boldsymbol\\phi)}\\left[\\mbox{f}[x]\\frac{\\partial}{\\partial \\boldsymbol\\phi} \\log\\bigl[ Pr(x|\\boldsymbol\\phi)\\bigr]\\right]\\nonumber \\\\\n",
+        "\\frac{\\partial}{\\partial \\boldsymbol\\phi} \\mathbb{E}_{Pr(x|\\boldsymbol\\phi)}\\bigl[\\text{f}[x]\\bigr] &=& \\mathbb{E}_{Pr(x|\\boldsymbol\\phi)}\\left[\\text{f}[x]\\frac{\\partial}{\\partial \\boldsymbol\\phi} \\log\\bigl[ Pr(x|\\boldsymbol\\phi)\\bigr]\\right]\\nonumber \\\\\n",
-        "&\\approx & \\frac{1}{I}\\sum_{i=1}^{I}\\mbox{f}[x_i]\\frac{\\partial}{\\partial \\boldsymbol\\phi} \\log\\bigl[ Pr(x_i|\\boldsymbol\\phi)\\bigr].\n",
+        "&\\approx & \\frac{1}{I}\\sum_{i=1}^{I}\\text{f}[x_i]\\frac{\\partial}{\\partial \\boldsymbol\\phi} \\log\\bigl[ Pr(x_i|\\boldsymbol\\phi)\\bigr].\n",
-        "\\end{eqnarray}\n",
+        "\\end{align}\n",
         "\n",
         "This method is known as the REINFORCE algorithm or score function estimator.  Problem 17.5 asks you to prove this relation.  Let's use this method to compute the gradient and compare.\n",
         "\n",
@@ -301,13 +295,15 @@
         "\\begin{equation}\n",
         " Pr(x|\\mu,\\sigma^2) = \\frac{1}{\\sqrt{2\\pi\\sigma^{2}}}\\exp\\left[-\\frac{(x-\\mu)^{2}}{2\\sigma^{2}}\\right].\n",
         "\\end{equation}\n"
-      ],
+      ]
-      "metadata": {
-        "id": "xoFR1wifc8-b"
-      }
     },
     {
       "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "4TUaxiWvASla"
+      },
+      "outputs": [],
       "source": [
         "def d_log_pr_x_given_phi(x,phi):\n",
         "  # TODO -- fill in this function\n",
@@ -333,15 +329,15 @@
         "\n",
         "\n",
         "  return deriv"
-      ],
+      ]
-      "metadata": {
-        "id": "4TUaxiWvASla"
-      },
-      "execution_count": null,
-      "outputs": []
     },
     {
       "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "0RSN32Rna_C_"
+      },
+      "outputs": [],
       "source": [
         "# Set the seed so the random numbers are all the same\n",
         "np.random.seed(0)\n",
@@ -352,15 +348,15 @@
         "\n",
         "deriv = compute_derivative_of_expectation_score_function(phi1, n_samples)\n",
         "print(\"Your value: \", deriv, \", True value:  5.724609927313369\")"
-      ],
+      ]
-      "metadata": {
-        "id": "0RSN32Rna_C_"
-      },
-      "execution_count": null,
-      "outputs": []
     },
     {
       "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "EM_i5zoyElHR"
+      },
+      "outputs": [],
       "source": [
         "phi_vals = np.arange(-1.5,1.5, 0.05)\n",
         "deriv_vals = np.zeros_like(phi_vals)\n",
@@ -373,24 +369,25 @@
         "ax.set_xlabel('Parameter $\\phi$')\n",
         "ax.set_ylabel('$\\partial/\\partial\\phi\\mathbb{E}_{Pr(x|\\phi)}[f[x]]$')\n",
         "plt.show()"
-      ],
+      ]
-      "metadata": {
-        "id": "EM_i5zoyElHR"
-      },
-      "execution_count": null,
-      "outputs": []
     },
     {
+      "attachments": {},
       "cell_type": "markdown",
-      "source": [
-        "This should look the same as the derivative that we computed with the reparameterization trick.  So, is there any advantage to one way or the other?  Let's compare the variances of the estimates\n"
-      ],
       "metadata": {
         "id": "1TWBiUC7bQSw"
-      }
+      },
+      "source": [
+        "This should look the same as the derivative that we computed with the reparameterization trick.  So, is there any advantage to one way or the other?  Let's compare the variances of the estimates\n"
+      ]
     },
     {
       "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "vV_Jx5bCbQGs"
+      },
+      "outputs": [],
       "source": [
         "n_estimate = 100\n",
         "n_sample = 1000\n",
@@ -403,21 +400,33 @@
         "\n",
         "print(\"Variance of reparameterization estimator\", np.var(reparam_estimates))\n",
         "print(\"Variance of score function estimator\", np.var(score_function_estimates))"
-      ],
+      ]
-      "metadata": {
-        "id": "vV_Jx5bCbQGs"
-      },
-      "execution_count": null,
-      "outputs": []
     },
     {
+      "attachments": {},
       "cell_type": "markdown",
-      "source": [
-        "The variance of the reparameterization estimator should be quite a bit lower than the score function estimator which is why it is preferred in this situation."
-      ],
       "metadata": {
         "id": "d-0tntSYdKPR"
-      }
+      },
+      "source": [
+        "The variance of the reparameterization estimator should be quite a bit lower than the score function estimator which is why it is preferred in this situation."
+      ]
     }
-  ]
+  ],
-}
+  "metadata": {
+    "colab": {
+      "authorship_tag": "ABX9TyOxO2/0DTH4n4zhC97qbagY",
+      "include_colab_link": true,
+      "provenance": []
+    },
+    "kernelspec": {
+      "display_name": "Python 3",
+      "name": "python3"
+    },
+    "language_info": {
+      "name": "python"
+    }
+  },
+  "nbformat": 4,
+  "nbformat_minor": 0
+}

Notebooks/Chap17/17_3_Importance_Sampling.ipynb

@@ -1,33 +1,22 @@
 {
-  "nbformat": 4,
-  "nbformat_minor": 0,
-  "metadata": {
-    "colab": {
-      "provenance": [],
-      "authorship_tag": "ABX9TyMvae+1cigwg2Htl6vt1Who",
-      "include_colab_link": true
-    },
-    "kernelspec": {
-      "name": "python3",
-      "display_name": "Python 3"
-    },
-    "language_info": {
-      "name": "python"
-    }
-  },
   "cells": [
     {
+      "attachments": {},
       "cell_type": "markdown",
       "metadata": {
-        "id": "view-in-github",
+        "colab_type": "text",
-        "colab_type": "text"
+        "id": "view-in-github"
       },
       "source": [
         "<a href=\"https://colab.research.google.com/github/udlbook/udlbook/blob/main/Notebooks/Chap17/17_3_Importance_Sampling.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
       ]
     },
     {
+      "attachments": {},
       "cell_type": "markdown",
+      "metadata": {
+        "id": "t9vk9Elugvmi"
+      },
       "source": [
         "# **Notebook 17.3: Importance sampling**\n",
         "\n",
@@ -36,25 +25,26 @@
         "Work through the cells below, running each cell in turn. In various places you will see the words \"TO DO\". Follow the instructions at these places and make predictions about what is going to happen or write code to complete the functions.\n",
         "\n",
         "Contact me at udlbookmail@gmail.com if you find any mistakes or have any suggestions."
-      ],
+      ]
-      "metadata": {
-        "id": "t9vk9Elugvmi"
-      }
     },
     {
       "cell_type": "code",
-      "source": [
+      "execution_count": null,
-        "import numpy as np\n",
-        "import matplotlib.pyplot as plt"
-      ],
       "metadata": {
         "id": "OLComQyvCIJ7"
       },
-      "execution_count": null,
+      "outputs": [],
-      "outputs": []
+      "source": [
+        "import numpy as np\n",
+        "import matplotlib.pyplot as plt"
+      ]
     },
     {
+      "attachments": {},
       "cell_type": "markdown",
+      "metadata": {
+        "id": "f7a6xqKjkmvT"
+      },
       "source": [
         "Let's approximate the expectation\n",
         "\n",
@@ -65,7 +55,7 @@
         "where\n",
         "\n",
         "\\begin{equation}\n",
-        "Pr(y)=\\mbox{Norm}_y[0,1]\n",
+        "Pr(y)=\\text{Norm}_y[0,1]\n",
         "\\end{equation}\n",
         "\n",
         "by drawing $I$ samples $y_i$ and using the formula:\n",
@@ -73,13 +63,15 @@
         "\\begin{equation}\n",
         "\\mathbb{E}_{y}\\Bigl[\\exp\\bigl[- (y-1)^4\\bigr]\\Bigr] \\approx \\frac{1}{I} \\sum_{i=1}^I \\exp\\bigl[-(y-1)^4 \\bigr]\n",
         "\\end{equation}"
-      ],
+      ]
-      "metadata": {
-        "id": "f7a6xqKjkmvT"
-      }
     },
     {
       "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "VjkzRr8o2ksg"
+      },
+      "outputs": [],
       "source": [
         "def f(y):\n",
         "  return np.exp(-(y-1) *(y-1) *(y-1) * (y-1))\n",
@@ -95,15 +87,15 @@
         "ax.set_xlabel(\"$y$\")\n",
         "ax.legend()\n",
         "plt.show()"
-      ],
+      ]
-      "metadata": {
-        "id": "VjkzRr8o2ksg"
-      },
-      "execution_count": null,
-      "outputs": []
     },
     {
       "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "LGAKHjUJnWmy"
+      },
+      "outputs": [],
       "source": [
         "def compute_expectation(n_samples):\n",
         "  # TODO -- compute this expectation\n",
@@ -114,15 +106,15 @@
         "\n",
         "\n",
         "  return expectation"
-      ],
+      ]
-      "metadata": {
-        "id": "LGAKHjUJnWmy"
-      },
-      "execution_count": null,
-      "outputs": []
     },
     {
       "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "nmvixMqgodIP"
+      },
+      "outputs": [],
       "source": [
         "# Set the seed so the random numbers are all the same\n",
         "np.random.seed(0)\n",
@@ -131,26 +123,27 @@
         "n_samples = 100000000\n",
         "expected_f= compute_expectation(n_samples)\n",
         "print(\"Your value: \", expected_f, \", True value:  0.43160702267383166\")"
-      ],
+      ]
-      "metadata": {
-        "id": "nmvixMqgodIP"
-      },
-      "execution_count": null,
-      "outputs": []
     },
     {
+      "attachments": {},
       "cell_type": "markdown",
+      "metadata": {
+        "id": "Jr4UPcqmnXCS"
+      },
       "source": [
         "Let's investigate how the variance of this approximation decreases as we increase the number of samples $N$.\n",
         "\n",
         "\n"
-      ],
+      ]
-      "metadata": {
-        "id": "Jr4UPcqmnXCS"
-      }
     },
     {
       "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "yrDp1ILUo08j"
+      },
+      "outputs": [],
       "source": [
         "def compute_mean_variance(n_sample):\n",
         "  n_estimate = 10000\n",
@@ -158,15 +151,15 @@
         "  for i in range(n_estimate):\n",
         "    estimates[i] = compute_expectation(n_sample.astype(int))\n",
         "  return np.mean(estimates), np.var(estimates)"
-      ],
+      ]
-      "metadata": {
-        "id": "yrDp1ILUo08j"
-      },
-      "execution_count": null,
-      "outputs": []
     },
     {
       "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "BcUVsodtqdey"
+      },
+      "outputs": [],
       "source": [
         "# Compute the mean and variance for 1,2,... 20 samples\n",
         "n_sample_all = np.array([1.,2,3,4,5,6,7,8,9,10,15,20,25,30,45,50,60,70,80,90,100,150,200,250,300,350,400,450,500])\n",
@@ -175,15 +168,15 @@
         "for i in range(len(n_sample_all)):\n",
         "  print(\"Computing mean and variance for expectation with %d samples\"%(n_sample_all[i]))\n",
         "  mean_all[i],variance_all[i] = compute_mean_variance(n_sample_all[i])"
-      ],
+      ]
-      "metadata": {
-        "id": "BcUVsodtqdey"
-      },
-      "execution_count": null,
-      "outputs": []
     },
     {
       "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "feXmyk0krpUi"
+      },
+      "outputs": [],
       "source": [
         "fig,ax = plt.subplots()\n",
         "ax.semilogx(n_sample_all, mean_all,'r-',label='mean estimate')\n",
@@ -193,38 +186,40 @@
         "ax.plot([0,500],[0.43160702267383166,0.43160702267383166],'k--',label='true value')\n",
         "ax.legend()\n",
         "plt.show()\n"
-      ],
+      ]
-      "metadata": {
-        "id": "feXmyk0krpUi"
-      },
-      "execution_count": null,
-      "outputs": []
     },
     {
+      "attachments": {},
       "cell_type": "markdown",
-      "source": [
-        "As you might expect, the more samples that we use to compute the approximate estimate, the lower the variance of the estimate."
-      ],
       "metadata": {
         "id": "XTUpxFlSuOl7"
-      }
+      },
+      "source": [
+        "As you might expect, the more samples that we use to compute the approximate estimate, the lower the variance of the estimate."
+      ]
     },
     {
+      "attachments": {},
       "cell_type": "markdown",
+      "metadata": {
+        "id": "6hxsl3Pxo1TT"
+      },
       "source": [
         " Now consider the function\n",
         " \\begin{equation}\n",
         " \\mbox{f}[y]= 20.446\\exp\\left[-(y-3)^4\\right],\n",
         " \\end{equation}\n",
         "\n",
-        "which decreases rapidly as we move away from the position $y=4$."
+        "which decreases rapidly as we move away from the position $y=3$."
-      ],
+      ]
-      "metadata": {
-        "id": "6hxsl3Pxo1TT"
-      }
     },
     {
       "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "znydVPW7sL4P"
+      },
+      "outputs": [],
       "source": [
         "def f2(y):\n",
         "  return 20.446*np.exp(- (y-3) *(y-3) *(y-3) * (y-3))\n",
@@ -236,46 +231,47 @@
         "ax.set_xlabel(\"$y$\")\n",
         "ax.legend()\n",
         "plt.show()"
-      ],
+      ]
-      "metadata": {
-        "id": "znydVPW7sL4P"
-      },
-      "execution_count": null,
-      "outputs": []
     },
     {
+      "attachments": {},
       "cell_type": "markdown",
+      "metadata": {
+        "id": "G9Xxo0OJsIqD"
+      },
       "source": [
         "Let's again, compute the expectation:\n",
         "\n",
-        "\\begin{eqnarray}\n",
+        "\\begin{align}\n",
-        "\\mathbb{E}_{y}\\left[\\mbox{f}[y]\\right] &=& \\int \\mbox{f}[y] Pr(y) dy\\\\\n",
+        "\\mathbb{E}_{y}\\left[\\text{f}[y]\\right] &=& \\int \\text{f}[y] Pr(y) dy\\\\\n",
-        "&\\approx& \\frac{1}{I} \\mbox{f}[y]\n",
+        "&\\approx& \\frac{1}{I} \\text{f}[y]\n",
-        "\\end{eqnarray}\n",
+        "\\end{align}\n",
         "\n",
-        "where $Pr(y)=\\mbox{Norm}_y[0,1]$ by approximating with samples $y_{i}$.\n"
+        "where $Pr(y)=\\text{Norm}_y[0,1]$ by approximating with samples $y_{i}$.\n"
-      ],
+      ]
-      "metadata": {
-        "id": "G9Xxo0OJsIqD"
-      }
     },
     {
       "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "l8ZtmkA2vH4y"
+      },
+      "outputs": [],
       "source": [
         "def compute_expectation2(n_samples):\n",
         "  y = np.random.normal(size=(n_samples,1))\n",
         "  expectation = np.mean(f2(y))\n",
         "\n",
         "  return expectation"
-      ],
+      ]
-      "metadata": {
-        "id": "l8ZtmkA2vH4y"
-      },
-      "execution_count": null,
-      "outputs": []
     },
     {
       "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "dfUQyJ-svZ6F"
+      },
+      "outputs": [],
       "source": [
         "# Set the seed so the random numbers are all the same\n",
         "np.random.seed(0)\n",
@@ -284,26 +280,27 @@
         "n_samples = 100000000\n",
         "expected_f2= compute_expectation2(n_samples)\n",
         "print(\"Expected value: \", expected_f2)"
-      ],
+      ]
-      "metadata": {
-        "id": "dfUQyJ-svZ6F"
-      },
-      "execution_count": null,
-      "outputs": []
     },
     {
+      "attachments": {},
       "cell_type": "markdown",
+      "metadata": {
+        "id": "2sVDqP0BvxqM"
+      },
       "source": [
         "I deliberately chose this function, because it's expectation is roughly the same as for the previous function.\n",
         "\n",
         "Again, let's look at the mean and the  variance of the estimates"
-      ],
+      ]
-      "metadata": {
-        "id": "2sVDqP0BvxqM"
-      }
     },
     {
       "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "mHnILRkOv0Ir"
+      },
+      "outputs": [],
       "source": [
         "def compute_mean_variance2(n_sample):\n",
         "  n_estimate = 10000\n",
@@ -318,15 +315,15 @@
         "for i in range(len(n_sample_all)):\n",
         "  print(\"Computing variance for expectation with %d samples\"%(n_sample_all[i]))\n",
         "  mean_all2[i], variance_all2[i] = compute_mean_variance2(n_sample_all[i])"
-      ],
+      ]
-      "metadata": {
-        "id": "mHnILRkOv0Ir"
-      },
-      "execution_count": null,
-      "outputs": []
     },
     {
       "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "FkCX-hxxAnsw"
+      },
+      "outputs": [],
       "source": [
         "fig,ax1 = plt.subplots()\n",
         "ax1.semilogx(n_sample_all, mean_all,'r-',label='mean estimate')\n",
@@ -348,39 +345,41 @@
         "ax2.set_title(\"Second function\")\n",
         "ax2.legend()\n",
         "plt.show()"
-      ],
+      ]
-      "metadata": {
-        "id": "FkCX-hxxAnsw"
-      },
-      "execution_count": null,
-      "outputs": []
     },
     {
+      "attachments": {},
       "cell_type": "markdown",
+      "metadata": {
+        "id": "EtBP6NeLwZqz"
+      },
       "source": [
         "You can see that the variance of the estimate of the second function is considerably worse than the estimate of the variance of estimate of the first function\n",
         "\n",
         "TODO:  Think about why this is."
-      ],
+      ]
-      "metadata": {
-        "id": "EtBP6NeLwZqz"
-      }
     },
     {
+      "attachments": {},
       "cell_type": "markdown",
+      "metadata": {
+        "id": "_wuF-NoQu1--"
+      },
       "source": [
         " Now let's repeat this experiment with the second function, but this time use importance sampling with auxiliary distribution:\n",
         "\n",
         " \\begin{equation}\n",
-        "   q(y)=\\mbox{Norm}_{y}[3,1]\n",
+        "   q(y)=\\text{Norm}_{y}[3,1]\n",
         " \\end{equation}\n"
-      ],
+      ]
-      "metadata": {
-        "id": "_wuF-NoQu1--"
-      }
     },
     {
       "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "jPm0AVYVIDnn"
+      },
+      "outputs": [],
       "source": [
         "def q_y(y):\n",
         "  return (1/np.sqrt(2*np.pi)) * np.exp(-0.5 * (y-3) * (y-3))\n",
@@ -395,15 +394,15 @@
         "  expectation = 0\n",
         "\n",
         "  return expectation"
-      ],
+      ]
-      "metadata": {
-        "id": "jPm0AVYVIDnn"
-      },
-      "execution_count": null,
-      "outputs": []
     },
     {
       "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "No2ByVvOM2yQ"
+      },
+      "outputs": [],
       "source": [
         "# Set the seed so the random numbers are all the same\n",
         "np.random.seed(0)\n",
@@ -412,15 +411,15 @@
         "n_samples = 100000000\n",
         "expected_f2= compute_expectation2b(n_samples)\n",
         "print(\"Your value: \", expected_f2,\", True value:  0.43163734204459125 \")"
-      ],
+      ]
-      "metadata": {
-        "id": "No2ByVvOM2yQ"
-      },
-      "execution_count": null,
-      "outputs": []
     },
     {
       "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "6v8Jc7z4M3Mk"
+      },
+      "outputs": [],
       "source": [
         "def compute_mean_variance2b(n_sample):\n",
         "  n_estimate = 10000\n",
@@ -435,15 +434,15 @@
         "for i in range(len(n_sample_all)):\n",
         "  print(\"Computing variance for expectation with %d samples\"%(n_sample_all[i]))\n",
         "  mean_all2b[i], variance_all2b[i] = compute_mean_variance2b(n_sample_all[i])"
-      ],
+      ]
-      "metadata": {
-        "id": "6v8Jc7z4M3Mk"
-      },
-      "execution_count": null,
-      "outputs": []
     },
     {
       "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "C0beD4sNNM3L"
+      },
+      "outputs": [],
       "source": [
         "fig,ax1 = plt.subplots()\n",
         "ax1.semilogx(n_sample_all, mean_all,'r-',label='mean estimate')\n",
@@ -476,21 +475,33 @@
         "ax2.set_title(\"Second function with importance sampling\")\n",
         "ax2.legend()\n",
         "plt.show()"
-      ],
+      ]
-      "metadata": {
-        "id": "C0beD4sNNM3L"
-      },
-      "execution_count": null,
-      "outputs": []
     },
     {
+      "attachments": {},
       "cell_type": "markdown",
-      "source": [
-        "You can see that the importance sampling technique has reduced the amount of variance for any given number of samples."
-      ],
       "metadata": {
         "id": "y8rgge9MNiOc"
-      }
+      },
+      "source": [
+        "You can see that the importance sampling technique has reduced the amount of variance for any given number of samples."
+      ]
     }
-  ]
+  ],
-}
+  "metadata": {
+    "colab": {
+      "authorship_tag": "ABX9TyNecz9/CDOggPSmy1LjT/Dv",
+      "include_colab_link": true,
+      "provenance": []
+    },
+    "kernelspec": {
+      "display_name": "Python 3",
+      "name": "python3"
+    },
+    "language_info": {
+      "name": "python"
+    }
+  },
+  "nbformat": 4,
+  "nbformat_minor": 0
+}

Notebooks/Chap18/18_1_Diffusion_Encoder.ipynb

@@ -1,26 +1,10 @@
 {
-  "nbformat": 4,
-  "nbformat_minor": 0,
-  "metadata": {
-    "colab": {
-      "provenance": [],
-      "authorship_tag": "ABX9TyMpC8kgLnXx0XQBtwNAQ4jJ",
-      "include_colab_link": true
-    },
-    "kernelspec": {
-      "name": "python3",
-      "display_name": "Python 3"
-    },
-    "language_info": {
-      "name": "python"
-    }
-  },
   "cells": [
     {
       "cell_type": "markdown",
       "metadata": {
-        "id": "view-in-github",
+        "colab_type": "text",
-        "colab_type": "text"
+        "id": "view-in-github"
       },
       "source": [
         "<a href=\"https://colab.research.google.com/github/udlbook/udlbook/blob/main/Notebooks/Chap18/18_1_Diffusion_Encoder.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
@@ -28,6 +12,9 @@
     },
     {
       "cell_type": "markdown",
+      "metadata": {
+        "id": "t9vk9Elugvmi"
+      },
       "source": [
         "# **Notebook 18.1: Diffusion Encoder**\n",
         "\n",
@@ -36,27 +23,29 @@
         "Work through the cells below, running each cell in turn. In various places you will see the words \"TO DO\". Follow the instructions at these places and make predictions about what is going to happen or write code to complete the functions.\n",
         "\n",
         "Contact me at udlbookmail@gmail.com if you find any mistakes or have any suggestions."
-      ],
+      ]
-      "metadata": {
-        "id": "t9vk9Elugvmi"
-      }
     },
     {
       "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "OLComQyvCIJ7"
+      },
+      "outputs": [],
       "source": [
         "import numpy as np\n",
         "import matplotlib.pyplot as plt\n",
         "from matplotlib.colors import ListedColormap\n",
         "from operator import itemgetter"
-      ],
+      ]
-      "metadata": {
-        "id": "OLComQyvCIJ7"
-      },
-      "execution_count": null,
-      "outputs": []
     },
     {
       "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "4PM8bf6lO0VE"
+      },
+      "outputs": [],
       "source": [
         "#Create pretty colormap as in book\n",
         "my_colormap_vals_hex =('2a0902', '2b0a03', '2c0b04', '2d0c05', '2e0c06', '2f0d07', '300d08', '310e09', '320f0a', '330f0b', '34100b', '35110c', '36110d', '37120e', '38120f', '39130f', '3a1410', '3b1411', '3c1511', '3d1612', '3e1613', '3f1713', '401714', '411814', '421915', '431915', '451a16', '461b16', '471b17', '481c17', '491d18', '4a1d18', '4b1e19', '4c1f19', '4d1f1a', '4e201b', '50211b', '51211c', '52221c', '53231d', '54231d', '55241e', '56251e', '57261f', '58261f', '592720', '5b2821', '5c2821', '5d2922', '5e2a22', '5f2b23', '602b23', '612c24', '622d25', '632e25', '652e26', '662f26', '673027', '683027', '693128', '6a3229', '6b3329', '6c342a', '6d342a', '6f352b', '70362c', '71372c', '72372d', '73382e', '74392e', '753a2f', '763a2f', '773b30', '783c31', '7a3d31', '7b3e32', '7c3e33', '7d3f33', '7e4034', '7f4134', '804235', '814236', '824336', '834437', '854538', '864638', '874739', '88473a', '89483a', '8a493b', '8b4a3c', '8c4b3c', '8d4c3d', '8e4c3e', '8f4d3f', '904e3f', '924f40', '935041', '945141', '955242', '965343', '975343', '985444', '995545', '9a5646', '9b5746', '9c5847', '9d5948', '9e5a49', '9f5a49', 'a05b4a', 'a15c4b', 'a35d4b', 'a45e4c', 'a55f4d', 'a6604e', 'a7614e', 'a8624f', 'a96350', 'aa6451', 'ab6552', 'ac6552', 'ad6653', 'ae6754', 'af6855', 'b06955', 'b16a56', 'b26b57', 'b36c58', 'b46d59', 'b56e59', 'b66f5a', 'b7705b', 'b8715c', 'b9725d', 'ba735d', 'bb745e', 'bc755f', 'bd7660', 'be7761', 'bf7862', 'c07962', 'c17a63', 'c27b64', 'c27c65', 'c37d66', 'c47e67', 'c57f68', 'c68068', 'c78169', 'c8826a', 'c9836b', 'ca846c', 'cb856d', 'cc866e', 'cd876f', 'ce886f', 'ce8970', 'cf8a71', 'd08b72', 'd18c73', 'd28d74', 'd38e75', 'd48f76', 'd59077', 'd59178', 'd69279', 'd7937a', 'd8957b', 'd9967b', 'da977c', 'da987d', 'db997e', 'dc9a7f', 'dd9b80', 'de9c81', 'de9d82', 'df9e83', 'e09f84', 'e1a185', 'e2a286', 'e2a387', 'e3a488', 'e4a589', 'e5a68a', 'e5a78b', 'e6a88c', 'e7aa8d', 'e7ab8e', 'e8ac8f', 'e9ad90', 'eaae91', 'eaaf92', 'ebb093', 'ecb295', 'ecb396', 'edb497', 'eeb598', 'eeb699', 'efb79a', 'efb99b', 'f0ba9c', 'f1bb9d', 'f1bc9e', 'f2bd9f', 'f2bfa1', 'f3c0a2', 'f3c1a3', 'f4c2a4', 'f5c3a5', 'f5c5a6', 'f6c6a7', 'f6c7a8', 'f7c8aa', 'f7c9ab', 'f8cbac', 'f8ccad', 'f8cdae', 'f9ceb0', 'f9d0b1', 'fad1b2', 'fad2b3', 'fbd3b4', 'fbd5b6', 'fbd6b7', 'fcd7b8', 'fcd8b9', 'fcdaba', 'fddbbc', 'fddcbd', 'fddebe', 'fddfbf', 'fee0c1', 'fee1c2', 'fee3c3', 'fee4c5', 'ffe5c6', 'ffe7c7', 'ffe8c9', 'ffe9ca', 'ffebcb', 'ffeccd', 'ffedce', 'ffefcf', 'fff0d1', 'fff2d2', 'fff3d3', 'fff4d5', 'fff6d6', 'fff7d8', 'fff8d9', 'fffada', 'fffbdc', 'fffcdd', 'fffedf', 'ffffe0')\n",
@@ -66,28 +55,28 @@
         "b = np.floor(my_colormap_vals_dec - r * 256 *256 - g * 256)\n",
         "my_colormap_vals = np.vstack((r,g,b)).transpose()/255.0\n",
         "my_colormap = ListedColormap(my_colormap_vals)"
-      ],
+      ]
-      "metadata": {
-        "id": "4PM8bf6lO0VE"
-      },
-      "execution_count": null,
-      "outputs": []
     },
     {
       "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "ONGRaQscfIOo"
+      },
+      "outputs": [],
       "source": [
         "# Probability distribution for normal\n",
         "def norm_pdf(x, mu, sigma):\n",
         "    return np.exp(-0.5 * (x-mu) * (x-mu) / (sigma * sigma)) / np.sqrt(2*np.pi*sigma*sigma)"
-      ],
+      ]
-      "metadata": {
-        "id": "ONGRaQscfIOo"
-      },
-      "execution_count": null,
-      "outputs": []
     },
     {
       "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "gZvG0MKhfY8Y"
+      },
+      "outputs": [],
       "source": [
         "# True distribution is a mixture of four Gaussians\n",
         "class TrueDataDistribution:\n",
@@ -108,15 +97,15 @@
         "    mu_list = list(itemgetter(*hidden)(self.mu))\n",
         "    sigma_list = list(itemgetter(*hidden)(self.sigma))\n",
         "    return mu_list + sigma_list * epsilon"
-      ],
+      ]
-      "metadata": {
-        "id": "gZvG0MKhfY8Y"
-      },
-      "execution_count": null,
-      "outputs": []
     },
     {
       "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "qXmej3TUuQyp"
+      },
+      "outputs": [],
       "source": [
         "# Define ground truth probability distribution that we will model\n",
         "true_dist = TrueDataDistribution()\n",
@@ -130,24 +119,24 @@
         "ax.set_ylim(0,1.0)\n",
         "ax.set_xlim(-3,3)\n",
         "plt.show()"
-      ],
+      ]
-      "metadata": {
-        "id": "qXmej3TUuQyp"
-      },
-      "execution_count": null,
-      "outputs": []
     },
     {
       "cell_type": "markdown",
-      "source": [
-        "Let's first implement the forward process"
-      ],
       "metadata": {
         "id": "XHdtfRP47YLy"
-      }
+      },
+      "source": [
+        "Let's first implement the forward process"
+      ]
     },
     {
       "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "hkApJ2VJlQuk"
+      },
+      "outputs": [],
       "source": [
         "# Do one step of diffusion (equation 18.1)\n",
         "def diffuse_one_step(z_t_minus_1, beta_t):\n",
@@ -157,24 +146,24 @@
         "  z_t = np.zeros_like(z_t_minus_1)\n",
         "\n",
         "  return z_t"
-      ],
+      ]
-      "metadata": {
-        "id": "hkApJ2VJlQuk"
-      },
-      "execution_count": null,
-      "outputs": []
     },
     {
       "cell_type": "markdown",
-      "source": [
-        "Now let's run the diffusion process for a whole bunch of samples"
-      ],
       "metadata": {
         "id": "ECAUfHNi9NVW"
-      }
+      },
+      "source": [
+        "Now let's run the diffusion process for a whole bunch of samples"
+      ]
     },
     {
       "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "M-TY5w9Q8LYW"
+      },
+      "outputs": [],
       "source": [
         "# Generate some samples\n",
         "n_sample = 10000\n",
@@ -192,24 +181,24 @@
         "\n",
         "for t in range(T):\n",
         "  samples[t+1,:] = diffuse_one_step(samples[t,:], beta)"
-      ],
+      ]
-      "metadata": {
-        "id": "M-TY5w9Q8LYW"
-      },
-      "execution_count": null,
-      "outputs": []
     },
     {
       "cell_type": "markdown",
-      "source": [
-        "Let's, plot the evolution of a few paths as in figure 18.2"
-      ],
       "metadata": {
         "id": "jYrAW6tN-gJ4"
-      }
+      },
+      "source": [
+        "Let's, plot the evolution of a few paths as in figure 18.2"
+      ]
     },
     {
       "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "4XU6CDZC_kFo"
+      },
+      "outputs": [],
       "source": [
         "fig, ax = plt.subplots()\n",
         "t_vals = np.arange(0,101,1)\n",
@@ -223,24 +212,24 @@
         "ax.set_xlabel('value')\n",
         "ax.set_ylabel('z_{t}')\n",
         "plt.show()"
-      ],
+      ]
-      "metadata": {
-        "id": "4XU6CDZC_kFo"
-      },
-      "execution_count": null,
-      "outputs": []
     },
     {
       "cell_type": "markdown",
-      "source": [
-        "Notice that the samples have a tendencey to move toward the center.  Now let's look at the histogram of the samples at each stage"
-      ],
       "metadata": {
         "id": "SGTYGGevAktz"
-      }
+      },
+      "source": [
+        "Notice that the samples have a tendency to move toward the center.  Now let's look at the histogram of the samples at each stage"
+      ]
     },
     {
       "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "bn5E5NzL-evM"
+      },
+      "outputs": [],
       "source": [
         "def draw_hist(z_t,title=''):\n",
         "  fig, ax = plt.subplots()\n",
@@ -248,17 +237,17 @@
         "  plt.hist(z_t , bins=np.arange(-3,3, 0.1), density = True)\n",
         "  ax.set_xlim([-3,3])\n",
         "  ax.set_ylim([0,1.0])\n",
-        "  ax.set_title('title')\n",
+        "  ax.set_title(title)\n",
         "  plt.show()"
-      ],
+      ]
-      "metadata": {
-        "id": "bn5E5NzL-evM"
-      },
-      "execution_count": null,
-      "outputs": []
     },
     {
       "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "pn_XD-EhBlwk"
+      },
+      "outputs": [],
       "source": [
         "draw_hist(samples[0,:],'Original data')\n",
         "draw_hist(samples[5,:],'Time step 5')\n",
@@ -267,33 +256,33 @@
         "draw_hist(samples[40,:],'Time step 40')\n",
         "draw_hist(samples[80,:],'Time step 80')\n",
         "draw_hist(samples[100,:],'Time step 100')"
-      ],
+      ]
-      "metadata": {
-        "id": "pn_XD-EhBlwk"
-      },
-      "execution_count": null,
-      "outputs": []
     },
     {
       "cell_type": "markdown",
-      "source": [
-        "You can clearly see that as the diffusion process continues, the data becomes more Gaussian."
-      ],
       "metadata": {
         "id": "skuLfGl5Czf4"
-      }
+      },
+      "source": [
+        "You can clearly see that as the diffusion process continues, the data becomes more Gaussian."
+      ]
     },
     {
       "cell_type": "markdown",
-      "source": [
-        "Now let's investigate the diffusion kernel as in figure 18.3 of the book.\n"
-      ],
       "metadata": {
         "id": "s37CBSzzK7wh"
-      }
+      },
+      "source": [
+        "Now let's investigate the diffusion kernel as in figure 18.3 of the book.\n"
+      ]
     },
     {
       "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "vL62Iym0LEtY"
+      },
+      "outputs": [],
       "source": [
         "def diffusion_kernel(x, t, beta):\n",
         "    # TODO -- write this function\n",
@@ -301,15 +290,15 @@
         "    dk_mean = 0.0 ; dk_std = 1.0\n",
         "\n",
         "    return dk_mean, dk_std"
-      ],
+      ]
-      "metadata": {
-        "id": "vL62Iym0LEtY"
-      },
-      "execution_count": null,
-      "outputs": []
     },
     {
       "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "KtP1KF8wMh8o"
+      },
+      "outputs": [],
       "source": [
         "def draw_prob_dist(x_plot_vals, prob_dist, title=''):\n",
         "  fig, ax = plt.subplots()\n",
@@ -363,47 +352,47 @@
         "    draw_prob_dist(x_plot_vals, diffusion_kernels[20,:],'$q(z_{20}|x)$')\n",
         "    draw_prob_dist(x_plot_vals, diffusion_kernels[40,:],'$q(z_{40}|x)$')\n",
         "    draw_prob_dist(x_plot_vals, diffusion_kernels[80,:],'$q(z_{80}|x)$')"
-      ],
+      ]
-      "metadata": {
-        "id": "KtP1KF8wMh8o"
-      },
-      "execution_count": null,
-      "outputs": []
     },
     {
       "cell_type": "code",
-      "source": [
+      "execution_count": null,
-        "x = -2\n",
-        "compute_and_plot_diffusion_kernels(x, T, beta, my_colormap)"
-      ],
       "metadata": {
         "id": "g8TcI5wtRQsx"
       },
-      "execution_count": null,
+      "outputs": [],
-      "outputs": []
+      "source": [
+        "x = -2\n",
+        "compute_and_plot_diffusion_kernels(x, T, beta, my_colormap)"
+      ]
     },
     {
       "cell_type": "markdown",
-      "source": [
-        "TODO -- Run this for different version of $x$ and check that you understand how the graphs change"
-      ],
       "metadata": {
         "id": "-RuN2lR28-hK"
-      }
+      },
+      "source": [
+        "TODO -- Run this for different version of $x$ and check that you understand how the graphs change"
+      ]
     },
     {
       "cell_type": "markdown",
+      "metadata": {
+        "id": "n-x6Whz2J_zy"
+      },
       "source": [
         "Finally, let's estimate the marginal distributions empirically and visualize them as in figure 18.4 of the book. This is only tractable because the data is in one dimension and we know the original distribution.\n",
         "\n",
         "The marginal distribution at time t is the sum of the diffusion kernels for each position x, weighted by the probability of seeing that value of x in the true distribution."
-      ],
+      ]
-      "metadata": {
-        "id": "n-x6Whz2J_zy"
-      }
     },
     {
       "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "YzN5duYpg7C-"
+      },
+      "outputs": [],
       "source": [
         "def diffusion_marginal(x_plot_vals, pr_x_true, t, beta):\n",
         "    # If time is zero then marginal is just original distribution\n",
@@ -414,7 +403,7 @@
         "    marginal_at_time_t = np.zeros_like(pr_x_true);\n",
         "\n",
         "\n",
-        "    # TODO Write ths function\n",
+        "    # TODO Write this function\n",
         "    # 1. For each x (value in x_plot_vals):\n",
         "      # 2. Compute the mean and variance of the diffusion kernel at time t\n",
         "      # 3. Compute pdf of this Gaussian at every x_plot_val\n",
@@ -427,15 +416,15 @@
         "\n",
         "\n",
         "    return marginal_at_time_t"
-      ],
+      ]
-      "metadata": {
-        "id": "YzN5duYpg7C-"
-      },
-      "execution_count": null,
-      "outputs": []
     },
     {
       "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "OgEU9sxjRaeO"
+      },
+      "outputs": [],
       "source": [
         "x_plot_vals = np.arange(-3,3,0.01)\n",
         "marginal_distributions = np.zeros((T+1,len(x_plot_vals)))\n",
@@ -460,12 +449,23 @@
         "draw_prob_dist(x_plot_vals, marginal_distributions[0,:],'$q(z_{0})$')\n",
         "draw_prob_dist(x_plot_vals, marginal_distributions[20,:],'$q(z_{20})$')\n",
         "draw_prob_dist(x_plot_vals, marginal_distributions[60,:],'$q(z_{60})$')"
-      ],
+      ]
-      "metadata": {
-        "id": "OgEU9sxjRaeO"
-      },
-      "execution_count": null,
-      "outputs": []
     }
-  ]
+  ],
-}
+  "metadata": {
+    "colab": {
+      "authorship_tag": "ABX9TyMpC8kgLnXx0XQBtwNAQ4jJ",
+      "include_colab_link": true,
+      "provenance": []
+    },
+    "kernelspec": {
+      "display_name": "Python 3",
+      "name": "python3"
+    },
+    "language_info": {
+      "name": "python"
+    }
+  },
+  "nbformat": 4,
+  "nbformat_minor": 0
+}

Notebooks/Chap18/18_2_1D_Diffusion_Model.ipynb

@@ -1,33 +1,22 @@
 {
-  "nbformat": 4,
-  "nbformat_minor": 0,
-  "metadata": {
-    "colab": {
-      "provenance": [],
-      "authorship_tag": "ABX9TyM4DdZDGoP1xGst+Nn+rwvt",
-      "include_colab_link": true
-    },
-    "kernelspec": {
-      "name": "python3",
-      "display_name": "Python 3"
-    },
-    "language_info": {
-      "name": "python"
-    }
-  },
   "cells": [
     {
+      "attachments": {},
       "cell_type": "markdown",
       "metadata": {
-        "id": "view-in-github",
+        "colab_type": "text",
-        "colab_type": "text"
+        "id": "view-in-github"
       },
       "source": [
         "<a href=\"https://colab.research.google.com/github/udlbook/udlbook/blob/main/Notebooks/Chap18/18_2_1D_Diffusion_Model.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
       ]
     },
     {
+      "attachments": {},
       "cell_type": "markdown",
+      "metadata": {
+        "id": "t9vk9Elugvmi"
+      },
       "source": [
         "# **Notebook 18.2: 1D Diffusion Model**\n",
         "\n",
@@ -36,13 +25,15 @@
         "Work through the cells below, running each cell in turn. In various places you will see the words \"TO DO\". Follow the instructions at these places and make predictions about what is going to happen or write code to complete the functions.\n",
         "\n",
         "Contact me at udlbookmail@gmail.com if you find any mistakes or have any suggestions."
-      ],
+      ]
-      "metadata": {
-        "id": "t9vk9Elugvmi"
-      }
     },
     {
       "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "OLComQyvCIJ7"
+      },
+      "outputs": [],
       "source": [
         "import numpy as np\n",
         "import matplotlib.pyplot as plt\n",
@@ -50,15 +41,15 @@
         "from operator import itemgetter\n",
         "from scipy import stats\n",
         "from IPython.display import display, clear_output"
-      ],
+      ]
-      "metadata": {
-        "id": "OLComQyvCIJ7"
-      },
-      "execution_count": null,
-      "outputs": []
     },
     {
       "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "4PM8bf6lO0VE"
+      },
+      "outputs": [],
       "source": [
         "#Create pretty colormap as in book\n",
         "my_colormap_vals_hex =('2a0902', '2b0a03', '2c0b04', '2d0c05', '2e0c06', '2f0d07', '300d08', '310e09', '320f0a', '330f0b', '34100b', '35110c', '36110d', '37120e', '38120f', '39130f', '3a1410', '3b1411', '3c1511', '3d1612', '3e1613', '3f1713', '401714', '411814', '421915', '431915', '451a16', '461b16', '471b17', '481c17', '491d18', '4a1d18', '4b1e19', '4c1f19', '4d1f1a', '4e201b', '50211b', '51211c', '52221c', '53231d', '54231d', '55241e', '56251e', '57261f', '58261f', '592720', '5b2821', '5c2821', '5d2922', '5e2a22', '5f2b23', '602b23', '612c24', '622d25', '632e25', '652e26', '662f26', '673027', '683027', '693128', '6a3229', '6b3329', '6c342a', '6d342a', '6f352b', '70362c', '71372c', '72372d', '73382e', '74392e', '753a2f', '763a2f', '773b30', '783c31', '7a3d31', '7b3e32', '7c3e33', '7d3f33', '7e4034', '7f4134', '804235', '814236', '824336', '834437', '854538', '864638', '874739', '88473a', '89483a', '8a493b', '8b4a3c', '8c4b3c', '8d4c3d', '8e4c3e', '8f4d3f', '904e3f', '924f40', '935041', '945141', '955242', '965343', '975343', '985444', '995545', '9a5646', '9b5746', '9c5847', '9d5948', '9e5a49', '9f5a49', 'a05b4a', 'a15c4b', 'a35d4b', 'a45e4c', 'a55f4d', 'a6604e', 'a7614e', 'a8624f', 'a96350', 'aa6451', 'ab6552', 'ac6552', 'ad6653', 'ae6754', 'af6855', 'b06955', 'b16a56', 'b26b57', 'b36c58', 'b46d59', 'b56e59', 'b66f5a', 'b7705b', 'b8715c', 'b9725d', 'ba735d', 'bb745e', 'bc755f', 'bd7660', 'be7761', 'bf7862', 'c07962', 'c17a63', 'c27b64', 'c27c65', 'c37d66', 'c47e67', 'c57f68', 'c68068', 'c78169', 'c8826a', 'c9836b', 'ca846c', 'cb856d', 'cc866e', 'cd876f', 'ce886f', 'ce8970', 'cf8a71', 'd08b72', 'd18c73', 'd28d74', 'd38e75', 'd48f76', 'd59077', 'd59178', 'd69279', 'd7937a', 'd8957b', 'd9967b', 'da977c', 'da987d', 'db997e', 'dc9a7f', 'dd9b80', 'de9c81', 'de9d82', 'df9e83', 'e09f84', 'e1a185', 'e2a286', 'e2a387', 'e3a488', 'e4a589', 'e5a68a', 'e5a78b', 'e6a88c', 'e7aa8d', 'e7ab8e', 'e8ac8f', 'e9ad90', 'eaae91', 'eaaf92', 'ebb093', 'ecb295', 'ecb396', 'edb497', 'eeb598', 'eeb699', 'efb79a', 'efb99b', 'f0ba9c', 'f1bb9d', 'f1bc9e', 'f2bd9f', 'f2bfa1', 'f3c0a2', 'f3c1a3', 'f4c2a4', 'f5c3a5', 'f5c5a6', 'f6c6a7', 'f6c7a8', 'f7c8aa', 'f7c9ab', 'f8cbac', 'f8ccad', 'f8cdae', 'f9ceb0', 'f9d0b1', 'fad1b2', 'fad2b3', 'fbd3b4', 'fbd5b6', 'fbd6b7', 'fcd7b8', 'fcd8b9', 'fcdaba', 'fddbbc', 'fddcbd', 'fddebe', 'fddfbf', 'fee0c1', 'fee1c2', 'fee3c3', 'fee4c5', 'ffe5c6', 'ffe7c7', 'ffe8c9', 'ffe9ca', 'ffebcb', 'ffeccd', 'ffedce', 'ffefcf', 'fff0d1', 'fff2d2', 'fff3d3', 'fff4d5', 'fff6d6', 'fff7d8', 'fff8d9', 'fffada', 'fffbdc', 'fffcdd', 'fffedf', 'ffffe0')\n",
@@ -68,28 +59,28 @@
         "b = np.floor(my_colormap_vals_dec - r * 256 *256 - g * 256)\n",
         "my_colormap_vals = np.vstack((r,g,b)).transpose()/255.0\n",
         "my_colormap = ListedColormap(my_colormap_vals)"
-      ],
+      ]
-      "metadata": {
-        "id": "4PM8bf6lO0VE"
-      },
-      "execution_count": null,
-      "outputs": []
     },
     {
       "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "ONGRaQscfIOo"
+      },
+      "outputs": [],
       "source": [
         "# Probability distribution for normal\n",
         "def norm_pdf(x, mu, sigma):\n",
         "    return np.exp(-0.5 * (x-mu) * (x-mu) / (sigma * sigma)) / np.sqrt(2*np.pi*sigma*sigma)"
-      ],
+      ]
-      "metadata": {
-        "id": "ONGRaQscfIOo"
-      },
-      "execution_count": null,
-      "outputs": []
     },
     {
       "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "gZvG0MKhfY8Y"
+      },
+      "outputs": [],
       "source": [
         "# True distribution is a mixture of four Gaussians\n",
         "class TrueDataDistribution:\n",
@@ -110,15 +101,15 @@
         "    mu_list = list(itemgetter(*hidden)(self.mu))\n",
         "    sigma_list = list(itemgetter(*hidden)(self.sigma))\n",
         "    return mu_list + sigma_list * epsilon"
-      ],
+      ]
-      "metadata": {
-        "id": "gZvG0MKhfY8Y"
-      },
-      "execution_count": null,
-      "outputs": []
     },
     {
       "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "iJu_uBiaeUVv"
+      },
+      "outputs": [],
       "source": [
         "# Define ground truth probability distribution that we will model\n",
         "true_dist = TrueDataDistribution()\n",
@@ -133,25 +124,26 @@
         "ax.set_ylim(0,1.0)\n",
         "ax.set_xlim(-3,3)\n",
         "plt.show()"
-      ],
+      ]
-      "metadata": {
-        "id": "iJu_uBiaeUVv"
-      },
-      "execution_count": null,
-      "outputs": []
     },
     {
+      "attachments": {},
       "cell_type": "markdown",
+      "metadata": {
+        "id": "DRHUG_41i4t_"
+      },
       "source": [
         "To train the model to describe this distribution, we'll need to generate pairs of samples drawn from $Pr(z_t|x)$ (diffusion kernel) and $q(z_{t-1}|z_{t},x)$ (equation 18.15).\n",
         "\n"
-      ],
+      ]
-      "metadata": {
-        "id": "DRHUG_41i4t_"
-      }
     },
     {
       "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "x6B8t72Ukscd"
+      },
+      "outputs": [],
       "source": [
         "# The diffusion kernel returns the parameters of Pr(z_{t}|x)\n",
         "def diffusion_kernel(x, t, beta):\n",
@@ -172,7 +164,7 @@
         "    # Find diffusion kernel for every x_train and draw samples\n",
         "    dk_mean, dk_std = diffusion_kernel(x_train, t, beta)\n",
         "    z_t = np.random.normal(size=x_train.shape) * dk_std + dk_mean\n",
-        "    # Find conditional diffusion distribution for each x_train, z pair and draw samlpes\n",
+        "    # Find conditional diffusion distribution for each x_train, z pair and draw samples\n",
         "    cd_mean, cd_std  = conditional_diffusion_distribution(x_train,z_t,t,beta)\n",
         "    if t == 1:\n",
         "      z_tminus1 = x_train\n",
@@ -180,24 +172,25 @@
         "      z_tminus1 = np.random.normal(size=x_train.shape) * cd_std + cd_mean\n",
         "\n",
         "    return z_t, z_tminus1"
-      ],
+      ]
-      "metadata": {
-        "id": "x6B8t72Ukscd"
-      },
-      "execution_count": null,
-      "outputs": []
     },
     {
+      "attachments": {},
       "cell_type": "markdown",
-      "source": [
-        "We also need models $\\mbox{f}_t[z_{t},\\phi_{t}]$ that map from $z_{t}$ to the mean of the distribution at time $z_{t-1}$.  We're just going to use a very hacky non-parametric model (basically a lookup table) that tells you the result based on the (quantized) input."
-      ],
       "metadata": {
         "id": "aSG_4uA8_zZ-"
-      }
+      },
+      "source": [
+        "We also need models $\\text{f}_t[z_{t},\\phi_{t}]$ that map from $z_{t}$ to the mean of the distribution at time $z_{t-1}$.  We're just going to use a very hacky non-parametric model (basically a lookup table) that tells you the result based on the (quantized) input."
+      ]
     },
     {
       "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "ZHViC0pL_yy5"
+      },
+      "outputs": [],
       "source": [
         "# This code is really ugly!  Don't look too closely at it!\n",
         "# All you need to know is that it is a model that trains from pairs zt, zt_minus1\n",
@@ -223,15 +216,15 @@
         "      bin_index = np.floor((zt+self.max_val)/self.inc)\n",
         "      bin_index = np.clip(bin_index,0, len(self.model)-1).astype('uint32')\n",
         "      return zt + self.model[bin_index]"
-      ],
+      ]
-      "metadata": {
-        "id": "ZHViC0pL_yy5"
-      },
-      "execution_count": null,
-      "outputs": []
     },
     {
       "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "CzVFybWoBygu"
+      },
+      "outputs": [],
       "source": [
         "# Sample data from distribution (this would usually be our collected training set)\n",
         "n_sample = 100000\n",
@@ -249,24 +242,25 @@
         "    all_models.append(NonParametricModel())\n",
         "    # The model at index t maps data from z_{t+1} to z_{t}\n",
         "    all_models[t].train(zt,zt_minus1)"
-      ],
+      ]
-      "metadata": {
-        "id": "CzVFybWoBygu"
-      },
-      "execution_count": null,
-      "outputs": []
     },
     {
+      "attachments": {},
       "cell_type": "markdown",
-      "source": [
-        "Now that we've learned the model, let's draw some samples from it.  We start at $z_{100}$ and use the model to predict $z_{99}$, then $z_{98}$ and so on until finally we get to $z_{1}$ and then $x$ (represented as $z_{0}$ here). We'll store all of the intermediate stages as well, so we can plot the trajectories.  See equations 18.16."
-      ],
       "metadata": {
         "id": "ZPc9SEvtl14U"
-      }
+      },
+      "source": [
+        "Now that we've learned the model, let's draw some samples from it.  We start at $z_{100}$ and use the model to predict $z_{99}$, then $z_{98}$ and so on until finally we get to $z_{1}$ and then $x$ (represented as $z_{0}$ here). We'll store all of the intermediate stages as well, so we can plot the trajectories.  See equations 18.16."
+      ]
     },
     {
       "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "A-ZMFOvACIOw"
+      },
+      "outputs": [],
       "source": [
         "def sample(model, T, sigma_t, n_samples):\n",
         "    # Create the output array\n",
@@ -295,24 +289,25 @@
         "            samples[t-1,:] = samples[t-1,:]\n",
         "\n",
         "    return samples"
-      ],
+      ]
-      "metadata": {
-        "id": "A-ZMFOvACIOw"
-      },
-      "execution_count": null,
-      "outputs": []
     },
     {
+      "attachments": {},
       "cell_type": "markdown",
-      "source": [
-        "Now let's run the diffusion process for a whole bunch of samples"
-      ],
       "metadata": {
         "id": "ECAUfHNi9NVW"
-      }
+      },
+      "source": [
+        "Now let's run the diffusion process for a whole bunch of samples"
+      ]
     },
     {
       "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "M-TY5w9Q8LYW"
+      },
+      "outputs": [],
       "source": [
         "sigma_t=0.12288\n",
         "n_samples = 100000\n",
@@ -329,24 +324,25 @@
         "plt.hist(sampled_data, bins=bins, density =True)\n",
         "ax.set_ylim(0, 0.8)\n",
         "plt.show()"
-      ],
+      ]
-      "metadata": {
-        "id": "M-TY5w9Q8LYW"
-      },
-      "execution_count": null,
-      "outputs": []
     },
     {
+      "attachments": {},
       "cell_type": "markdown",
-      "source": [
-        "Let's, plot the evolution of a few of the paths as in figure 18.7 (paths are from bottom to top now)."
-      ],
       "metadata": {
         "id": "jYrAW6tN-gJ4"
-      }
+      },
+      "source": [
+        "Let's, plot the evolution of a few of the paths as in figure 18.7 (paths are from bottom to top now)."
+      ]
     },
     {
       "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "4XU6CDZC_kFo"
+      },
+      "outputs": [],
       "source": [
         "fig, ax = plt.subplots()\n",
         "t_vals = np.arange(0,101,1)\n",
@@ -360,21 +356,33 @@
         "ax.set_xlabel('value')\n",
         "ax.set_ylabel('z_{t}')\n",
         "plt.show()"
-      ],
+      ]
-      "metadata": {
-        "id": "4XU6CDZC_kFo"
-      },
-      "execution_count": null,
-      "outputs": []
     },
     {
+      "attachments": {},
       "cell_type": "markdown",
-      "source": [
-        "Notice that the samples have a tendency to move from positions that are near the center at time 100 to positions that are high in the true probability distribution at time 0"
-      ],
       "metadata": {
         "id": "SGTYGGevAktz"
-      }
+      },
+      "source": [
+        "Notice that the samples have a tendency to move from positions that are near the center at time 100 to positions that are high in the true probability distribution at time 0"
+      ]
     }
-  ]
+  ],
-}
+  "metadata": {
+    "colab": {
+      "authorship_tag": "ABX9TyM4DdZDGoP1xGst+Nn+rwvt",
+      "include_colab_link": true,
+      "provenance": []
+    },
+    "kernelspec": {
+      "display_name": "Python 3",
+      "name": "python3"
+    },
+    "language_info": {
+      "name": "python"
+    }
+  },
+  "nbformat": 4,
+  "nbformat_minor": 0
+}

Notebooks/Chap18/18_3_Reparameterized_Model.ipynb

@@ -1,33 +1,22 @@
 {
-  "nbformat": 4,
-  "nbformat_minor": 0,
-  "metadata": {
-    "colab": {
-      "provenance": [],
-      "authorship_tag": "ABX9TyNd+D0/IVWXtU2GKsofyk2d",
-      "include_colab_link": true
-    },
-    "kernelspec": {
-      "name": "python3",
-      "display_name": "Python 3"
-    },
-    "language_info": {
-      "name": "python"
-    }
-  },
   "cells": [
     {
+      "attachments": {},
       "cell_type": "markdown",
       "metadata": {
-        "id": "view-in-github",
+        "colab_type": "text",
-        "colab_type": "text"
+        "id": "view-in-github"
       },
       "source": [
         "<a href=\"https://colab.research.google.com/github/udlbook/udlbook/blob/main/Notebooks/Chap18/18_3_Reparameterized_Model.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
       ]
     },
     {
+      "attachments": {},
       "cell_type": "markdown",
+      "metadata": {
+        "id": "t9vk9Elugvmi"
+      },
       "source": [
         "# **Notebook 18.3: 1D Reparameterized model**\n",
         "\n",
@@ -36,13 +25,15 @@
         "Work through the cells below, running each cell in turn. In various places you will see the words \"TO DO\". Follow the instructions at these places and make predictions about what is going to happen or write code to complete the functions.\n",
         "\n",
         "Contact me at udlbookmail@gmail.com if you find any mistakes or have any suggestions."
-      ],
+      ]
-      "metadata": {
-        "id": "t9vk9Elugvmi"
-      }
     },
     {
       "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "OLComQyvCIJ7"
+      },
+      "outputs": [],
       "source": [
         "import numpy as np\n",
         "import matplotlib.pyplot as plt\n",
@@ -50,15 +41,15 @@
         "from operator import itemgetter\n",
         "from scipy import stats\n",
         "from IPython.display import display, clear_output"
-      ],
+      ]
-      "metadata": {
-        "id": "OLComQyvCIJ7"
-      },
-      "execution_count": null,
-      "outputs": []
     },
     {
       "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "4PM8bf6lO0VE"
+      },
+      "outputs": [],
       "source": [
         "#Create pretty colormap as in book\n",
         "my_colormap_vals_hex =('2a0902', '2b0a03', '2c0b04', '2d0c05', '2e0c06', '2f0d07', '300d08', '310e09', '320f0a', '330f0b', '34100b', '35110c', '36110d', '37120e', '38120f', '39130f', '3a1410', '3b1411', '3c1511', '3d1612', '3e1613', '3f1713', '401714', '411814', '421915', '431915', '451a16', '461b16', '471b17', '481c17', '491d18', '4a1d18', '4b1e19', '4c1f19', '4d1f1a', '4e201b', '50211b', '51211c', '52221c', '53231d', '54231d', '55241e', '56251e', '57261f', '58261f', '592720', '5b2821', '5c2821', '5d2922', '5e2a22', '5f2b23', '602b23', '612c24', '622d25', '632e25', '652e26', '662f26', '673027', '683027', '693128', '6a3229', '6b3329', '6c342a', '6d342a', '6f352b', '70362c', '71372c', '72372d', '73382e', '74392e', '753a2f', '763a2f', '773b30', '783c31', '7a3d31', '7b3e32', '7c3e33', '7d3f33', '7e4034', '7f4134', '804235', '814236', '824336', '834437', '854538', '864638', '874739', '88473a', '89483a', '8a493b', '8b4a3c', '8c4b3c', '8d4c3d', '8e4c3e', '8f4d3f', '904e3f', '924f40', '935041', '945141', '955242', '965343', '975343', '985444', '995545', '9a5646', '9b5746', '9c5847', '9d5948', '9e5a49', '9f5a49', 'a05b4a', 'a15c4b', 'a35d4b', 'a45e4c', 'a55f4d', 'a6604e', 'a7614e', 'a8624f', 'a96350', 'aa6451', 'ab6552', 'ac6552', 'ad6653', 'ae6754', 'af6855', 'b06955', 'b16a56', 'b26b57', 'b36c58', 'b46d59', 'b56e59', 'b66f5a', 'b7705b', 'b8715c', 'b9725d', 'ba735d', 'bb745e', 'bc755f', 'bd7660', 'be7761', 'bf7862', 'c07962', 'c17a63', 'c27b64', 'c27c65', 'c37d66', 'c47e67', 'c57f68', 'c68068', 'c78169', 'c8826a', 'c9836b', 'ca846c', 'cb856d', 'cc866e', 'cd876f', 'ce886f', 'ce8970', 'cf8a71', 'd08b72', 'd18c73', 'd28d74', 'd38e75', 'd48f76', 'd59077', 'd59178', 'd69279', 'd7937a', 'd8957b', 'd9967b', 'da977c', 'da987d', 'db997e', 'dc9a7f', 'dd9b80', 'de9c81', 'de9d82', 'df9e83', 'e09f84', 'e1a185', 'e2a286', 'e2a387', 'e3a488', 'e4a589', 'e5a68a', 'e5a78b', 'e6a88c', 'e7aa8d', 'e7ab8e', 'e8ac8f', 'e9ad90', 'eaae91', 'eaaf92', 'ebb093', 'ecb295', 'ecb396', 'edb497', 'eeb598', 'eeb699', 'efb79a', 'efb99b', 'f0ba9c', 'f1bb9d', 'f1bc9e', 'f2bd9f', 'f2bfa1', 'f3c0a2', 'f3c1a3', 'f4c2a4', 'f5c3a5', 'f5c5a6', 'f6c6a7', 'f6c7a8', 'f7c8aa', 'f7c9ab', 'f8cbac', 'f8ccad', 'f8cdae', 'f9ceb0', 'f9d0b1', 'fad1b2', 'fad2b3', 'fbd3b4', 'fbd5b6', 'fbd6b7', 'fcd7b8', 'fcd8b9', 'fcdaba', 'fddbbc', 'fddcbd', 'fddebe', 'fddfbf', 'fee0c1', 'fee1c2', 'fee3c3', 'fee4c5', 'ffe5c6', 'ffe7c7', 'ffe8c9', 'ffe9ca', 'ffebcb', 'ffeccd', 'ffedce', 'ffefcf', 'fff0d1', 'fff2d2', 'fff3d3', 'fff4d5', 'fff6d6', 'fff7d8', 'fff8d9', 'fffada', 'fffbdc', 'fffcdd', 'fffedf', 'ffffe0')\n",
@@ -68,28 +59,28 @@
         "b = np.floor(my_colormap_vals_dec - r * 256 *256 - g * 256)\n",
         "my_colormap_vals = np.vstack((r,g,b)).transpose()/255.0\n",
         "my_colormap = ListedColormap(my_colormap_vals)"
-      ],
+      ]
-      "metadata": {
-        "id": "4PM8bf6lO0VE"
-      },
-      "execution_count": null,
-      "outputs": []
     },
     {
       "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "ONGRaQscfIOo"
+      },
+      "outputs": [],
       "source": [
         "# Probability distribution for normal\n",
         "def norm_pdf(x, mu, sigma):\n",
         "    return np.exp(-0.5 * (x-mu) * (x-mu) / (sigma * sigma)) / np.sqrt(2*np.pi*sigma*sigma)"
-      ],
+      ]
-      "metadata": {
-        "id": "ONGRaQscfIOo"
-      },
-      "execution_count": null,
-      "outputs": []
     },
     {
       "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "gZvG0MKhfY8Y"
+      },
+      "outputs": [],
       "source": [
         "# True distribution is a mixture of four Gaussians\n",
         "class TrueDataDistribution:\n",
@@ -110,15 +101,15 @@
         "    mu_list = list(itemgetter(*hidden)(self.mu))\n",
         "    sigma_list = list(itemgetter(*hidden)(self.sigma))\n",
         "    return mu_list + sigma_list * epsilon"
-      ],
+      ]
-      "metadata": {
-        "id": "gZvG0MKhfY8Y"
-      },
-      "execution_count": null,
-      "outputs": []
     },
     {
       "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "iJu_uBiaeUVv"
+      },
+      "outputs": [],
       "source": [
         "# Define ground truth probability distribution that we will model\n",
         "true_dist = TrueDataDistribution()\n",
@@ -133,25 +124,26 @@
         "ax.set_ylim(0,1.0)\n",
         "ax.set_xlim(-3,3)\n",
         "plt.show()"
-      ],
+      ]
-      "metadata": {
-        "id": "iJu_uBiaeUVv"
-      },
-      "execution_count": null,
-      "outputs": []
     },
     {
+      "attachments": {},
       "cell_type": "markdown",
+      "metadata": {
+        "id": "DRHUG_41i4t_"
+      },
       "source": [
         "To train the model to describe this distribution, we'll need to generate pairs of samples drawn from $Pr(z_t|x)$ (diffusion kernel) and $q(z_{t-1}|z_{t},x)$ (equation 18.15).\n",
         "\n"
-      ],
+      ]
-      "metadata": {
-        "id": "DRHUG_41i4t_"
-      }
     },
     {
       "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "x6B8t72Ukscd"
+      },
+      "outputs": [],
       "source": [
         "# Return z_t (the argument of g_{t}[] in the loss function in algorithm 18.1) and epsilon\n",
         "def get_data_pairs(x_train,t,beta):\n",
@@ -161,24 +153,25 @@
         "    z_t = np.ones_like(x_train)\n",
         "\n",
         "    return z_t, epsilon"
-      ],
+      ]
-      "metadata": {
-        "id": "x6B8t72Ukscd"
-      },
-      "execution_count": null,
-      "outputs": []
     },
     {
+      "attachments": {},
       "cell_type": "markdown",
-      "source": [
-        "We also need models $\\mbox{g}_t[z_{t},\\phi_{t}]$ that map from $z_{t}$ to the noise $\\epsilon$ that was added.  We're just going to use a very hacky non-parametric model (basically a lookup table) that tells you the result based on the (quantized) input."
-      ],
       "metadata": {
         "id": "aSG_4uA8_zZ-"
-      }
+      },
+      "source": [
+        "We also need models $\\text{g}_t[z_{t},\\phi_{t}]$ that map from $z_{t}$ to the noise $\\epsilon$ that was added.  We're just going to use a very hacky non-parametric model (basically a lookup table) that tells you the result based on the (quantized) input."
+      ]
     },
     {
       "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "ZHViC0pL_yy5"
+      },
+      "outputs": [],
       "source": [
         "# This code is really ugly!  Don't look too closely at it!\n",
         "# All you need to know is that it is a model that trains from pairs zt, zt_minus1\n",
@@ -204,15 +197,15 @@
         "      bin_index = np.floor((zt+self.max_val)/self.inc)\n",
         "      bin_index = np.clip(bin_index,0, len(self.model)-1).astype('uint32')\n",
         "      return self.model[bin_index]"
-      ],
+      ]
-      "metadata": {
-        "id": "ZHViC0pL_yy5"
-      },
-      "execution_count": null,
-      "outputs": []
     },
     {
       "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "CzVFybWoBygu"
+      },
+      "outputs": [],
       "source": [
         "# Sample data from distribution (this would usually be our collected training set)\n",
         "n_sample = 100000\n",
@@ -230,24 +223,25 @@
         "    all_models.append(NonParametricModel())\n",
         "    # The model at index t maps data from z_{t+1} to epsilon\n",
         "    all_models[t].train(zt,epsilon)"
-      ],
+      ]
-      "metadata": {
-        "id": "CzVFybWoBygu"
-      },
-      "execution_count": null,
-      "outputs": []
     },
     {
+      "attachments": {},
       "cell_type": "markdown",
-      "source": [
-        "Now that we've learned the model, let's draw some samples from it.  We start at $z_{100}$ and use the model to predict $z_{99}$, then $z_{98}$ and so on until finally we get to $z_{1}$ and then $x$ (represented as $z_{0}$ here). We'll store all of the intermediate stages as well, so we can plot the trajectories.  See algorithm 18.2"
-      ],
       "metadata": {
         "id": "ZPc9SEvtl14U"
-      }
+      },
+      "source": [
+        "Now that we've learned the model, let's draw some samples from it.  We start at $z_{100}$ and use the model to predict $z_{99}$, then $z_{98}$ and so on until finally we get to $z_{1}$ and then $x$ (represented as $z_{0}$ here). We'll store all of the intermediate stages as well, so we can plot the trajectories.  See algorithm 18.2"
+      ]
     },
     {
       "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "A-ZMFOvACIOw"
+      },
+      "outputs": [],
       "source": [
         "def sample(model, T, sigma_t, n_samples):\n",
         "    # Create the output array\n",
@@ -277,24 +271,25 @@
         "            samples[t-1,:] = samples[t-1,:]\n",
         "\n",
         "    return samples"
-      ],
+      ]
-      "metadata": {
-        "id": "A-ZMFOvACIOw"
-      },
-      "execution_count": null,
-      "outputs": []
     },
     {
+      "attachments": {},
       "cell_type": "markdown",
-      "source": [
-        "Now let's run the diffusion process for a whole bunch of samples"
-      ],
       "metadata": {
         "id": "ECAUfHNi9NVW"
-      }
+      },
+      "source": [
+        "Now let's run the diffusion process for a whole bunch of samples"
+      ]
     },
     {
       "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "M-TY5w9Q8LYW"
+      },
+      "outputs": [],
       "source": [
         "sigma_t=0.12288\n",
         "n_samples = 100000\n",
@@ -311,24 +306,25 @@
         "plt.hist(sampled_data, bins=bins, density =True)\n",
         "ax.set_ylim(0, 0.8)\n",
         "plt.show()"
-      ],
+      ]
-      "metadata": {
-        "id": "M-TY5w9Q8LYW"
-      },
-      "execution_count": null,
-      "outputs": []
     },
     {
+      "attachments": {},
       "cell_type": "markdown",
-      "source": [
-        "Let's, plot the evolution of a few of the paths as in figure 18.7 (paths are from bottom to top now)."
-      ],
       "metadata": {
         "id": "jYrAW6tN-gJ4"
-      }
+      },
+      "source": [
+        "Let's, plot the evolution of a few of the paths as in figure 18.7 (paths are from bottom to top now)."
+      ]
     },
     {
       "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "4XU6CDZC_kFo"
+      },
+      "outputs": [],
       "source": [
         "fig, ax = plt.subplots()\n",
         "t_vals = np.arange(0,101,1)\n",
@@ -342,21 +338,33 @@
         "ax.set_xlabel('value')\n",
         "ax.set_ylabel('z_{t}')\n",
         "plt.show()"
-      ],
+      ]
-      "metadata": {
-        "id": "4XU6CDZC_kFo"
-      },
-      "execution_count": null,
-      "outputs": []
     },
     {
+      "attachments": {},
       "cell_type": "markdown",
-      "source": [
-        "Notice that the samples have a tendency to move from positions that are near the center at time 100 to positions that are high in the true probability distribution at time 0"
-      ],
       "metadata": {
         "id": "SGTYGGevAktz"
-      }
+      },
+      "source": [
+        "Notice that the samples have a tendency to move from positions that are near the center at time 100 to positions that are high in the true probability distribution at time 0"
+      ]
     }
-  ]
+  ],
-}
+  "metadata": {
+    "colab": {
+      "authorship_tag": "ABX9TyNd+D0/IVWXtU2GKsofyk2d",
+      "include_colab_link": true,
+      "provenance": []
+    },
+    "kernelspec": {
+      "display_name": "Python 3",
+      "name": "python3"
+    },
+    "language_info": {
+      "name": "python"
+    }
+  },
+  "nbformat": 4,
+  "nbformat_minor": 0
+}

Notebooks/Chap18/18_4_Families_of_Diffusion_Models.ipynb

@@ -1,33 +1,22 @@
 {
-  "nbformat": 4,
-  "nbformat_minor": 0,
-  "metadata": {
-    "colab": {
-      "provenance": [],
-      "authorship_tag": "ABX9TyNFSvISBXo/Z1l+onknF2Gw",
-      "include_colab_link": true
-    },
-    "kernelspec": {
-      "name": "python3",
-      "display_name": "Python 3"
-    },
-    "language_info": {
-      "name": "python"
-    }
-  },
   "cells": [
     {
+      "attachments": {},
       "cell_type": "markdown",
       "metadata": {
-        "id": "view-in-github",
+        "colab_type": "text",
-        "colab_type": "text"
+        "id": "view-in-github"
       },
       "source": [
         "<a href=\"https://colab.research.google.com/github/udlbook/udlbook/blob/main/Notebooks/Chap18/18_4_Families_of_Diffusion_Models.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
       ]
     },
     {
+      "attachments": {},
       "cell_type": "markdown",
+      "metadata": {
+        "id": "t9vk9Elugvmi"
+      },
       "source": [
         "# **Notebook 18.4: Families of diffusion models**\n",
         "\n",
@@ -36,13 +25,15 @@
         "Work through the cells below, running each cell in turn. In various places you will see the words \"TO DO\". Follow the instructions at these places and make predictions about what is going to happen or write code to complete the functions.\n",
         "\n",
         "Contact me at udlbookmail@gmail.com if you find any mistakes or have any suggestions."
-      ],
+      ]
-      "metadata": {
-        "id": "t9vk9Elugvmi"
-      }
     },
     {
       "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "OLComQyvCIJ7"
+      },
+      "outputs": [],
       "source": [
         "import numpy as np\n",
         "import matplotlib.pyplot as plt\n",
@@ -50,15 +41,15 @@
         "from operator import itemgetter\n",
         "from scipy import stats\n",
         "from IPython.display import display, clear_output"
-      ],
+      ]
-      "metadata": {
-        "id": "OLComQyvCIJ7"
-      },
-      "execution_count": null,
-      "outputs": []
     },
     {
       "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "4PM8bf6lO0VE"
+      },
+      "outputs": [],
       "source": [
         "#Create pretty colormap as in book\n",
         "my_colormap_vals_hex =('2a0902', '2b0a03', '2c0b04', '2d0c05', '2e0c06', '2f0d07', '300d08', '310e09', '320f0a', '330f0b', '34100b', '35110c', '36110d', '37120e', '38120f', '39130f', '3a1410', '3b1411', '3c1511', '3d1612', '3e1613', '3f1713', '401714', '411814', '421915', '431915', '451a16', '461b16', '471b17', '481c17', '491d18', '4a1d18', '4b1e19', '4c1f19', '4d1f1a', '4e201b', '50211b', '51211c', '52221c', '53231d', '54231d', '55241e', '56251e', '57261f', '58261f', '592720', '5b2821', '5c2821', '5d2922', '5e2a22', '5f2b23', '602b23', '612c24', '622d25', '632e25', '652e26', '662f26', '673027', '683027', '693128', '6a3229', '6b3329', '6c342a', '6d342a', '6f352b', '70362c', '71372c', '72372d', '73382e', '74392e', '753a2f', '763a2f', '773b30', '783c31', '7a3d31', '7b3e32', '7c3e33', '7d3f33', '7e4034', '7f4134', '804235', '814236', '824336', '834437', '854538', '864638', '874739', '88473a', '89483a', '8a493b', '8b4a3c', '8c4b3c', '8d4c3d', '8e4c3e', '8f4d3f', '904e3f', '924f40', '935041', '945141', '955242', '965343', '975343', '985444', '995545', '9a5646', '9b5746', '9c5847', '9d5948', '9e5a49', '9f5a49', 'a05b4a', 'a15c4b', 'a35d4b', 'a45e4c', 'a55f4d', 'a6604e', 'a7614e', 'a8624f', 'a96350', 'aa6451', 'ab6552', 'ac6552', 'ad6653', 'ae6754', 'af6855', 'b06955', 'b16a56', 'b26b57', 'b36c58', 'b46d59', 'b56e59', 'b66f5a', 'b7705b', 'b8715c', 'b9725d', 'ba735d', 'bb745e', 'bc755f', 'bd7660', 'be7761', 'bf7862', 'c07962', 'c17a63', 'c27b64', 'c27c65', 'c37d66', 'c47e67', 'c57f68', 'c68068', 'c78169', 'c8826a', 'c9836b', 'ca846c', 'cb856d', 'cc866e', 'cd876f', 'ce886f', 'ce8970', 'cf8a71', 'd08b72', 'd18c73', 'd28d74', 'd38e75', 'd48f76', 'd59077', 'd59178', 'd69279', 'd7937a', 'd8957b', 'd9967b', 'da977c', 'da987d', 'db997e', 'dc9a7f', 'dd9b80', 'de9c81', 'de9d82', 'df9e83', 'e09f84', 'e1a185', 'e2a286', 'e2a387', 'e3a488', 'e4a589', 'e5a68a', 'e5a78b', 'e6a88c', 'e7aa8d', 'e7ab8e', 'e8ac8f', 'e9ad90', 'eaae91', 'eaaf92', 'ebb093', 'ecb295', 'ecb396', 'edb497', 'eeb598', 'eeb699', 'efb79a', 'efb99b', 'f0ba9c', 'f1bb9d', 'f1bc9e', 'f2bd9f', 'f2bfa1', 'f3c0a2', 'f3c1a3', 'f4c2a4', 'f5c3a5', 'f5c5a6', 'f6c6a7', 'f6c7a8', 'f7c8aa', 'f7c9ab', 'f8cbac', 'f8ccad', 'f8cdae', 'f9ceb0', 'f9d0b1', 'fad1b2', 'fad2b3', 'fbd3b4', 'fbd5b6', 'fbd6b7', 'fcd7b8', 'fcd8b9', 'fcdaba', 'fddbbc', 'fddcbd', 'fddebe', 'fddfbf', 'fee0c1', 'fee1c2', 'fee3c3', 'fee4c5', 'ffe5c6', 'ffe7c7', 'ffe8c9', 'ffe9ca', 'ffebcb', 'ffeccd', 'ffedce', 'ffefcf', 'fff0d1', 'fff2d2', 'fff3d3', 'fff4d5', 'fff6d6', 'fff7d8', 'fff8d9', 'fffada', 'fffbdc', 'fffcdd', 'fffedf', 'ffffe0')\n",
@@ -68,28 +59,28 @@
         "b = np.floor(my_colormap_vals_dec - r * 256 *256 - g * 256)\n",
         "my_colormap_vals = np.vstack((r,g,b)).transpose()/255.0\n",
         "my_colormap = ListedColormap(my_colormap_vals)"
-      ],
+      ]
-      "metadata": {
-        "id": "4PM8bf6lO0VE"
-      },
-      "execution_count": null,
-      "outputs": []
     },
     {
       "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "ONGRaQscfIOo"
+      },
+      "outputs": [],
       "source": [
         "# Probability distribution for normal\n",
         "def norm_pdf(x, mu, sigma):\n",
         "    return np.exp(-0.5 * (x-mu) * (x-mu) / (sigma * sigma)) / np.sqrt(2*np.pi*sigma*sigma)"
-      ],
+      ]
-      "metadata": {
-        "id": "ONGRaQscfIOo"
-      },
-      "execution_count": null,
-      "outputs": []
     },
     {
       "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "gZvG0MKhfY8Y"
+      },
+      "outputs": [],
       "source": [
         "# True distribution is a mixture of four Gaussians\n",
         "class TrueDataDistribution:\n",
@@ -110,15 +101,15 @@
         "    mu_list = list(itemgetter(*hidden)(self.mu))\n",
         "    sigma_list = list(itemgetter(*hidden)(self.sigma))\n",
         "    return mu_list + sigma_list * epsilon"
-      ],
+      ]
-      "metadata": {
-        "id": "gZvG0MKhfY8Y"
-      },
-      "execution_count": null,
-      "outputs": []
     },
     {
       "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "iJu_uBiaeUVv"
+      },
+      "outputs": [],
       "source": [
         "# Define ground truth probability distribution that we will model\n",
         "true_dist = TrueDataDistribution()\n",
@@ -133,25 +124,26 @@
         "ax.set_ylim(0,1.0)\n",
         "ax.set_xlim(-3,3)\n",
         "plt.show()"
-      ],
+      ]
-      "metadata": {
-        "id": "iJu_uBiaeUVv"
-      },
-      "execution_count": null,
-      "outputs": []
     },
     {
+      "attachments": {},
       "cell_type": "markdown",
+      "metadata": {
+        "id": "DRHUG_41i4t_"
+      },
       "source": [
         "To train the model to describe this distribution, we'll need to generate pairs of samples drawn from $Pr(z_t|x)$ (diffusion kernel) and $q(z_{t-1}|z_{t},x)$ (equation 18.15).\n",
         "\n"
-      ],
+      ]
-      "metadata": {
-        "id": "DRHUG_41i4t_"
-      }
     },
     {
       "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "x6B8t72Ukscd"
+      },
+      "outputs": [],
       "source": [
         "# Return z_t (the argument of g_{t}[] in the loss function in algorithm 18.1) and epsilon\n",
         "def get_data_pairs(x_train,t,beta):\n",
@@ -161,24 +153,25 @@
         "    z_t = x_train * np.sqrt(alpha_t) + np.sqrt(1-alpha_t) * epsilon\n",
         "\n",
         "    return z_t, epsilon"
-      ],
+      ]
-      "metadata": {
-        "id": "x6B8t72Ukscd"
-      },
-      "execution_count": null,
-      "outputs": []
     },
     {
+      "attachments": {},
       "cell_type": "markdown",
-      "source": [
-        "We also need models $\\mbox{g}_t[z_{t},\\phi_{t}]$ that map from $z_{t}$ to the noise $\\epsilon$ that was added.  We're just going to use a very hacky non-parametric model (basically a lookup table) that tells you the result based on the (quantized) input."
-      ],
       "metadata": {
         "id": "aSG_4uA8_zZ-"
-      }
+      },
+      "source": [
+        "We also need models $\\text{g}_t[z_{t},\\phi_{t}]$ that map from $z_{t}$ to the noise $\\epsilon$ that was added.  We're just going to use a very hacky non-parametric model (basically a lookup table) that tells you the result based on the (quantized) input."
+      ]
     },
     {
       "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "ZHViC0pL_yy5"
+      },
+      "outputs": [],
       "source": [
         "# This code is really ugly!  Don't look too closely at it!\n",
         "# All you need to know is that it is a model that trains from pairs zt, zt_minus1\n",
@@ -204,15 +197,15 @@
         "      bin_index = np.floor((zt+self.max_val)/self.inc)\n",
         "      bin_index = np.clip(bin_index,0, len(self.model)-1).astype('uint32')\n",
         "      return self.model[bin_index]"
-      ],
+      ]
-      "metadata": {
-        "id": "ZHViC0pL_yy5"
-      },
-      "execution_count": null,
-      "outputs": []
     },
     {
       "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "CzVFybWoBygu"
+      },
+      "outputs": [],
       "source": [
         "# Sample data from distribution (this would usually be our collected training set)\n",
         "n_sample = 100000\n",
@@ -230,15 +223,14 @@
         "    all_models.append(NonParametricModel())\n",
         "    # The model at index t maps data from z_{t+1} to epsilon\n",
         "    all_models[t].train(zt,epsilon)"
-      ],
+      ]
-      "metadata": {
-        "id": "CzVFybWoBygu"
-      },
-      "execution_count": null,
-      "outputs": []
     },
     {
+      "attachments": {},
       "cell_type": "markdown",
+      "metadata": {
+        "id": "ZPc9SEvtl14U"
+      },
       "source": [
         "Now that we've learned the model, let's draw some samples from it.  We start at $z_{100}$ and use the model to predict $z_{99}$, then $z_{98}$ and so on until finally we get to $z_{1}$ and then $x$ (represented as $z_{0}$ here). We'll store all of the intermediate stages as well, so we can plot the trajectories.\n",
         "\n",
@@ -247,17 +239,19 @@
         "One such model is the denoising diffusion implicit model, which has a sampling step:\n",
         "\n",
         "\\begin{equation}\n",
-        "\\mathbf{z}_{t-1} = \\sqrt{\\alpha_{t-1}}\\left(\\frac{\\mathbf{z}_{t}-\\sqrt{1-\\alpha_{t}}\\mbox{g}_t[\\mathbf{z}_{t},\\boldsymbol\\phi]}{\\sqrt{\\alpha_{t}}}\\right) + \\sqrt{1-\\alpha_{t-1}-\\sigma^2}\\mbox{g}_t[\\mathbf{z}_{t},\\boldsymbol\\phi]+\\sigma\\epsilon\n",
+        "\\mathbf{z}_{t-1} = \\sqrt{\\alpha_{t-1}}\\left(\\frac{\\mathbf{z}_{t}-\\sqrt{1-\\alpha_{t}}\\text{g}_t[\\mathbf{z}_{t},\\boldsymbol\\phi]}{\\sqrt{\\alpha_{t}}}\\right) + \\sqrt{1-\\alpha_{t-1}-\\sigma^2}\\text{g}_t[\\mathbf{z}_{t},\\boldsymbol\\phi]+\\sigma\\epsilon\n",
         "\\end{equation}\n",
         "\n",
         "(see equation 12 of the denoising [diffusion implicit models paper ](https://arxiv.org/pdf/2010.02502.pdf).\n"
-      ],
+      ]
-      "metadata": {
-        "id": "ZPc9SEvtl14U"
-      }
     },
     {
       "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "A-ZMFOvACIOw"
+      },
+      "outputs": [],
       "source": [
         "def sample_ddim(model, T, sigma_t, n_samples):\n",
         "    # Create the output array\n",
@@ -283,24 +277,25 @@
         "        if t>0:\n",
         "            samples[t-1,:] = samples[t-1,:]+ np.random.standard_normal(n_samples) * sigma_t\n",
         "    return samples"
-      ],
+      ]
-      "metadata": {
-        "id": "A-ZMFOvACIOw"
-      },
-      "execution_count": null,
-      "outputs": []
     },
     {
+      "attachments": {},
       "cell_type": "markdown",
-      "source": [
-        "Now let's run the diffusion process for a whole bunch of samples"
-      ],
       "metadata": {
         "id": "ECAUfHNi9NVW"
-      }
+      },
+      "source": [
+        "Now let's run the diffusion process for a whole bunch of samples"
+      ]
     },
     {
       "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "M-TY5w9Q8LYW"
+      },
+      "outputs": [],
       "source": [
         "# Now we'll set the noise to a MUCH smaller level\n",
         "sigma_t=0.001\n",
@@ -318,24 +313,25 @@
         "plt.hist(sampled_data, bins=bins, density =True)\n",
         "ax.set_ylim(0, 0.8)\n",
         "plt.show()"
-      ],
+      ]
-      "metadata": {
-        "id": "M-TY5w9Q8LYW"
-      },
-      "execution_count": null,
-      "outputs": []
     },
     {
+      "attachments": {},
       "cell_type": "markdown",
-      "source": [
-        "Let's, plot the evolution of a few of the paths as in figure 18.7 (paths are from bottom to top now)."
-      ],
       "metadata": {
         "id": "jYrAW6tN-gJ4"
-      }
+      },
+      "source": [
+        "Let's, plot the evolution of a few of the paths as in figure 18.7 (paths are from bottom to top now)."
+      ]
     },
     {
       "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "4XU6CDZC_kFo"
+      },
+      "outputs": [],
       "source": [
         "fig, ax = plt.subplots()\n",
         "t_vals = np.arange(0,101,1)\n",
@@ -349,35 +345,37 @@
         "ax.set_xlabel('value')\n",
         "ax.set_ylabel('z_{t}')\n",
         "plt.show()"
-      ],
+      ]
-      "metadata": {
-        "id": "4XU6CDZC_kFo"
-      },
-      "execution_count": null,
-      "outputs": []
     },
     {
+      "attachments": {},
       "cell_type": "markdown",
-      "source": [
-        "The samples have a tendency to move from positions that are near the center at time 100 to positions that are high in the true probability distribution at time 0"
-      ],
       "metadata": {
         "id": "SGTYGGevAktz"
-      }
+      },
+      "source": [
+        "The samples have a tendency to move from positions that are near the center at time 100 to positions that are high in the true probability distribution at time 0"
+      ]
     },
     {
+      "attachments": {},
       "cell_type": "markdown",
+      "metadata": {
+        "id": "Z-LZp_fMXxRt"
+      },
       "source": [
         "Let's now sample from the accelerated model, that requires fewer models.  Again, we don't need to learn anything new -- this is just the reverse process that corresponds to a different forward process that is compatible with the same diffusion kernel.\n",
         "\n",
         "There's nothing to do here except read the code.  It uses the same DDIM model as you just implemented in the previous step, but it jumps timesteps five at a time."
-      ],
+      ]
-      "metadata": {
-        "id": "Z-LZp_fMXxRt"
-      }
     },
     {
       "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "3Z0erjGbYj1u"
+      },
+      "outputs": [],
       "source": [
         "def sample_accelerated(model, T, sigma_t, n_steps, n_samples):\n",
         "    # Create the output array\n",
@@ -403,24 +401,25 @@
         "      if t>0:\n",
         "            samples[c_step-1,:] = samples[c_step-1,:]+ np.random.standard_normal(n_samples) * sigma_t\n",
         "    return samples"
-      ],
+      ]
-      "metadata": {
-        "id": "3Z0erjGbYj1u"
-      },
-      "execution_count": null,
-      "outputs": []
     },
     {
+      "attachments": {},
       "cell_type": "markdown",
-      "source": [
-        "Now let's draw a bunch of samples from the model"
-      ],
       "metadata": {
         "id": "D3Sm_WYrcuED"
-      }
+      },
+      "source": [
+        "Now let's draw a bunch of samples from the model"
+      ]
     },
     {
       "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "UB45c7VMcGy-"
+      },
+      "outputs": [],
       "source": [
         "sigma_t=0.11\n",
         "n_samples = 100000\n",
@@ -438,15 +437,15 @@
         "plt.hist(sampled_data, bins=bins, density =True)\n",
         "ax.set_ylim(0, 0.9)\n",
         "plt.show()"
-      ],
+      ]
-      "metadata": {
-        "id": "UB45c7VMcGy-"
-      },
-      "execution_count": null,
-      "outputs": []
     },
     {
       "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "Luv-6w84c_qO"
+      },
+      "outputs": [],
       "source": [
         "fig, ax = plt.subplots()\n",
         "step_increment = 100/ n_steps\n",
@@ -464,21 +463,32 @@
         "ax.set_xlabel('value')\n",
         "ax.set_ylabel('z_{t}')\n",
         "plt.show()"
-      ],
+      ]
-      "metadata": {
-        "id": "Luv-6w84c_qO"
-      },
-      "execution_count": null,
-      "outputs": []
     },
     {
       "cell_type": "code",
-      "source": [],
+      "execution_count": null,
       "metadata": {
         "id": "LSJi72f0kw_e"
       },
-      "execution_count": null,
+      "outputs": [],
-      "outputs": []
+      "source": []
     }
-  ]
+  ],
-}
+  "metadata": {
+    "colab": {
+      "authorship_tag": "ABX9TyNFSvISBXo/Z1l+onknF2Gw",
+      "include_colab_link": true,
+      "provenance": []
+    },
+    "kernelspec": {
+      "display_name": "Python 3",
+      "name": "python3"
+    },
+    "language_info": {
+      "name": "python"
+    }
+  },
+  "nbformat": 4,
+  "nbformat_minor": 0
+}

Notebooks/Chap19/19_1_Markov_Decision_Processes.ipynb

@@ -598,7 +598,7 @@
       "source": [
         "def markov_decision_process_step_deterministic(state, transition_probabilities_given_action, reward_structure, policy):\n",
         "  # TODO -- complete this function.\n",
-        "  # For each state, theres is a corresponding action.\n",
+        "  # For each state, there's is a corresponding action.\n",
         "  # Draw the next state based on the current state and that action\n",
         "  # and calculate the reward\n",
         "  # Replace this line:\n",
@@ -683,7 +683,7 @@
       "source": [
         "def markov_decision_process_step_stochastic(state, transition_probabilities_given_action, reward_structure, stochastic_policy):\n",
         "  # TODO -- complete this function.\n",
-        "  # For each state, theres is a corresponding distribution over actions\n",
+        "  # For each state, there's is a corresponding distribution over actions\n",
         "  # Draw a sample from that distribution to get the action\n",
         "  # Draw the next state based on the current state and that action\n",
         "  # and calculate the reward\n",
@@ -733,4 +733,4 @@
       "outputs": []
     }
   ]
-}
+}

Notebooks/Chap19/19_4_Temporal_Difference_Methods.ipynb

@@ -31,7 +31,7 @@
       "source": [
         "# **Notebook 19.4: Temporal difference methods**\n",
         "\n",
-        "This notebook investigates temporal differnece methods for  tabular reinforcement learning as described in section 19.3.3 of the book\n",
+        "This notebook investigates temporal difference methods for  tabular reinforcement learning as described in section 19.3.3 of the book\n",
         "\n",
         "Work through the cells below, running each cell in turn. In various places you will see the words \"TO DO\". Follow the instructions at these places and make predictions about what is going to happen or write code to complete the functions.\n",
         "\n",

Notebooks/Chap19/19_5_Control_Variates.ipynb

@@ -57,7 +57,7 @@
     {
       "cell_type": "markdown",
       "source": [
-        "Genearate from our two variables, $a$ and $b$.  We are interested in estimating the mean of $a$, but we can use $b$$ to improve our estimates if it is correlated"
+        "Generate from our two variables, $a$ and $b$.  We are interested in estimating the mean of $a$, but we can use $b$$ to improve our estimates if it is correlated"
       ],
       "metadata": {
         "id": "uwmhcAZBzTRO"

Notebooks/Chap20/20_2_Full_Batch_Gradient_Descent.ipynb

@@ -0,0 +1,296 @@
+{
+  "nbformat": 4,
+  "nbformat_minor": 0,
+  "metadata": {
+    "colab": {
+      "provenance": [],
+      "authorship_tag": "ABX9TyOo4vm4MXcIvAzVlMCaLikH",
+      "include_colab_link": true
+    },
+    "kernelspec": {
+      "name": "python3",
+      "display_name": "Python 3"
+    },
+    "language_info": {
+      "name": "python"
+    }
+  },
+  "cells": [
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "view-in-github",
+        "colab_type": "text"
+      },
+      "source": [
+        "<a href=\"https://colab.research.google.com/github/udlbook/udlbook/blob/main/Notebooks/Chap20/20_2_Full_Batch_Gradient_Descent.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "# **Notebook 20.2: Full Batch Gradient Descent**\n",
+        "\n",
+        "This notebook investigates training a network with full batch gradient descent as in figure 20.2.  There is also a version (notebook takes a long time to run), but this didn't speed it up much for me.  If you run out of CoLab time,  you'll need to download the Python file and run locally.\n",
+        "\n",
+        "Work through the cells below, running each cell in turn. In various places you will see the words \"TO DO\". Follow the instructions at these places and make predictions about what is going to happen or write code to complete the functions.\n",
+        "\n",
+        "Contact me at udlbookmail@gmail.com if you find any mistakes or have any suggestions."
+      ],
+      "metadata": {
+        "id": "t9vk9Elugvmi"
+      }
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "# Run this if you're in a Colab to make a local copy of the MNIST 1D repository\n",
+        "!git clone https://github.com/greydanus/mnist1d"
+      ],
+      "metadata": {
+        "id": "D5yLObtZCi9J"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "import numpy as np\n",
+        "import os\n",
+        "import torch, torch.nn as nn\n",
+        "from torch.utils.data import TensorDataset, DataLoader\n",
+        "from torch.optim.lr_scheduler import StepLR\n",
+        "import matplotlib.pyplot as plt\n",
+        "import mnist1d\n",
+        "import random\n",
+        "from IPython.display import display, clear_output"
+      ],
+      "metadata": {
+        "id": "YrXWAH7sUWvU"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "args = mnist1d.data.get_dataset_args()\n",
+        "data = mnist1d.data.get_dataset(args, path='./mnist1d_data.pkl', download=False, regenerate=False)\n",
+        "\n",
+        "# The training and test input and outputs are in\n",
+        "# data['x'], data['y']\n",
+        "print(\"Examples in training set: {}\".format(len(data['y'])))\n",
+        "print(\"Length of each example: {}\".format(data['x'].shape[-1]))"
+      ],
+      "metadata": {
+        "id": "twI72ZCrCt5z"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "Define the network"
+      ],
+      "metadata": {
+        "id": "_sFvRDGrl4qe"
+      }
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "# Data is length forty, and there are 10 classes\n",
+        "D_i = 40\n",
+        "D_o = 10\n",
+        "\n",
+        "# create model with one hidden layer and 298 hidden units\n",
+        "model_1_layer = nn.Sequential(\n",
+        "nn.Linear(D_i, 298),\n",
+        "nn.ReLU(),\n",
+        "nn.Linear(298, D_o))\n",
+        "\n",
+        "\n",
+        "# TODO -- create model with three hidden layers and 100 hidden units per layer\n",
+        "# Replace this line\n",
+        "model_2_layer = nn.Sequential(nn.Linear(D_i, D_o))\n",
+        "\n",
+        "\n",
+        "\n",
+        "# TODO -- Create model with three hidden layers and 75 hidden units per layer\n",
+        "# Replace this line\n",
+        "model_3_layer = nn.Sequential(nn.Linear(D_i, D_o))\n",
+        "\n",
+        "\n",
+        "\n",
+        "# TODO create model with four hidden layers and 63 hidden units per layer\n",
+        "# Replace this line\n",
+        "model_4_layer = nn.Sequential(nn.Linear(D_i, D_o))\n",
+        "\n"
+      ],
+      "metadata": {
+        "id": "FslroPJJffrh"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "# He initialization of weights\n",
+        "def weights_init(layer_in):\n",
+        "  if isinstance(layer_in, nn.Linear):\n",
+        "    nn.init.kaiming_uniform_(layer_in.weight)\n",
+        "    layer_in.bias.data.fill_(0.0)"
+      ],
+      "metadata": {
+        "id": "YgLaex1pfhqz"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "def train_model(model, train_data_x, train_data_y, n_epoch):\n",
+        "  print(\"This is going to take a long time!\")\n",
+        "  # choose cross entropy loss function (equation 5.24 in the loss notes)\n",
+        "  loss_function = nn.CrossEntropyLoss()\n",
+        "  # construct SGD optimizer and initialize learning rate to small value and momentum to 0\n",
+        "  optimizer = torch.optim.SGD(model.parameters(), lr = 0.0025, momentum=0.0)\n",
+        "  # create 100 dummy data points and store in data loader class\n",
+        "  x_train = torch.tensor(train_data_x.transpose().astype('float32'))\n",
+        "  y_train = torch.tensor(train_data_y.astype('long'))\n",
+        "\n",
+        "  # load the data into a class that creates the batches -- full batch as there are 4000 examples\n",
+        "  data_loader = DataLoader(TensorDataset(x_train,y_train), batch_size=4000, shuffle=False, worker_init_fn=np.random.seed(1))\n",
+        "\n",
+        "  # Initialize model weights\n",
+        "  model.apply(weights_init)\n",
+        "\n",
+        "  # store the errors percentage at each point\n",
+        "  errors_train = np.zeros((n_epoch))\n",
+        "\n",
+        "  for epoch in range(n_epoch):\n",
+        "    # loop over batches\n",
+        "    for i, data in enumerate(data_loader):\n",
+        "      # retrieve inputs and labels for this batch\n",
+        "      x_batch, y_batch = data\n",
+        "      # zero the parameter gradients\n",
+        "      optimizer.zero_grad()\n",
+        "      # forward pass -- calculate model output\n",
+        "      pred = model(x_batch)\n",
+        "      # compute the loss\n",
+        "      loss = loss_function(pred, y_batch)\n",
+        "      # Store the errors\n",
+        "      _, predicted_train_class = torch.max(pred.data, 1)\n",
+        "      errors_train[epoch] = 100 - 100 * (predicted_train_class == y_train).float().sum() / len(y_train)\n",
+        "      # backward pass\n",
+        "      loss.backward()\n",
+        "      # SGD update\n",
+        "      optimizer.step()\n",
+        "\n",
+        "      if epoch % 10 == 0:\n",
+        "        clear_output(wait=True)\n",
+        "        display(\"Epoch %d, errors_train %3.3f\"%(epoch, errors_train[epoch]))\n",
+        "\n",
+        "  return errors_train"
+      ],
+      "metadata": {
+        "id": "NYw8I_3mmX5c"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "# Load in the data\n",
+        "train_data_x = data['x'].transpose()\n",
+        "train_data_y = data['y']\n",
+        "# Print out sizes\n",
+        "print(\"Train data: %d examples (columns), each of which has %d dimensions (rows)\"%((train_data_x.shape[1],train_data_x.shape[0])))"
+      ],
+      "metadata": {
+        "id": "4FE3HQ_vedXO"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "# Train the models\n",
+        "errors_four_layers = train_model(model_4_layer, train_data_x, train_data_y, n_epoch=200000)"
+      ],
+      "metadata": {
+        "id": "b56wdODqemF1"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "errors_three_layers = train_model(model_3_layer, train_data_x, train_data_y, n_epoch=200000)\n"
+      ],
+      "metadata": {
+        "id": "hqY-MJVPnCBV"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "errors_two_layers = train_model(model_2_layer, train_data_x, train_data_y, n_epoch=200000)\n"
+      ],
+      "metadata": {
+        "id": "T61jfpNGnDGj"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "errors_one_layer = train_model(model_1_layer, train_data_x, train_data_y, n_epoch=500000)"
+      ],
+      "metadata": {
+        "id": "HO8ZFgYqnEQe"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "# Plot the results\n",
+        "fig, ax = plt.subplots()\n",
+        "ax.plot(errors_one_layer,'r-',label='one layer')\n",
+        "ax.plot(errors_two_layers,'g-',label='two layers')\n",
+        "ax.plot(errors_three_layers,'b-',label='three layers')\n",
+        "ax.plot(errors_four_layers,'m-',label='four layers')\n",
+        "ax.set_ylim(0,100)\n",
+        "ax.set_xlabel('Epoch'); ax.set_ylabel('Percent error')\n",
+        "ax.legend()\n",
+        "plt.show()"
+      ],
+      "metadata": {
+        "id": "pYL0YMI5oNSR"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [],
+      "metadata": {
+        "id": "wJerga3M7eDw"
+      },
+      "execution_count": null,
+      "outputs": []
+    }
+  ]
+}

Notebooks/Chap20/20_2_Full_Batch_Gradient_Descent_GPU.ipynb

@@ -0,0 +1,303 @@
+{
+  "nbformat": 4,
+  "nbformat_minor": 0,
+  "metadata": {
+    "colab": {
+      "provenance": [],
+      "gpuType": "T4",
+      "authorship_tag": "ABX9TyMjPBfDONmjqTSyEQDP2gjY",
+      "include_colab_link": true
+    },
+    "kernelspec": {
+      "name": "python3",
+      "display_name": "Python 3"
+    },
+    "language_info": {
+      "name": "python"
+    },
+    "accelerator": "GPU"
+  },
+  "cells": [
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "view-in-github",
+        "colab_type": "text"
+      },
+      "source": [
+        "<a href=\"https://colab.research.google.com/github/udlbook/udlbook/blob/main/Notebooks/Chap20/20_2_Full_Batch_Gradient_Descent_GPU.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "# **Notebook 20.2: Full Batch Gradient Descent**\n",
+        "\n",
+        "This notebook investigates training a network with full batch gradient descent as in figure 20.2.  This is the GPU version (notebook takes a long time to run).  If you are using Colab then you need to go change the runtime type to GPU on the Runtime menu.  Even then, you may run out of time.  If that's the case, you'll need to download the Python file and run locally.\n",
+        "\n",
+        "Work through the cells below, running each cell in turn. In various places you will see the words \"TO DO\". Follow the instructions at these places and make predictions about what is going to happen or write code to complete the functions.\n",
+        "\n",
+        "Contact me at udlbookmail@gmail.com if you find any mistakes or have any suggestions.\n",
+        "\n"
+      ],
+      "metadata": {
+        "id": "t9vk9Elugvmi"
+      }
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "# Run this if you're in a Colab to make a local copy of the MNIST 1D repository\n",
+        "!git clone https://github.com/greydanus/mnist1d"
+      ],
+      "metadata": {
+        "id": "D5yLObtZCi9J"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "import numpy as np\n",
+        "import os\n",
+        "import torch, torch.nn as nn\n",
+        "from torch.utils.data import TensorDataset, DataLoader\n",
+        "from torch.optim.lr_scheduler import StepLR\n",
+        "import matplotlib.pyplot as plt\n",
+        "import mnist1d\n",
+        "import random\n",
+        "from IPython.display import display, clear_output\n",
+        "\n",
+        "\n",
+        "# Try attaching to GPU\n",
+        "DEVICE = str(torch.device('cuda' if torch.cuda.is_available() else 'cpu'))\n",
+        "print('Using:', DEVICE)"
+      ],
+      "metadata": {
+        "id": "YrXWAH7sUWvU"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "args = mnist1d.data.get_dataset_args()\n",
+        "data = mnist1d.data.get_dataset(args, path='./mnist1d_data.pkl', download=False, regenerate=False)\n",
+        "\n",
+        "# The training and test input and outputs are in\n",
+        "# data['x'], data['y']\n",
+        "print(\"Examples in training set: {}\".format(len(data['y'])))\n",
+        "print(\"Length of each example: {}\".format(data['x'].shape[-1]))"
+      ],
+      "metadata": {
+        "id": "twI72ZCrCt5z"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "Define the network"
+      ],
+      "metadata": {
+        "id": "_sFvRDGrl4qe"
+      }
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "# Data is length forty, and there are 10 classes\n",
+        "D_i = 40\n",
+        "D_o = 10\n",
+        "\n",
+        "# create model with one hidden layer and 298 hidden units\n",
+        "model_1_layer = nn.Sequential(\n",
+        "nn.Linear(D_i, 298),\n",
+        "nn.ReLU(),\n",
+        "nn.Linear(298, D_o))\n",
+        "\n",
+        "\n",
+        "# TODO -- create model with three hidden layers and 100 hidden units per layer\n",
+        "# Replace this line\n",
+        "model_2_layer = nn.Sequential(nn.Linear(D_i, D_o))\n",
+        "\n",
+        "# TODO -- Create model with three hidden layers and 75 hidden units per layer\n",
+        "# Replace this line\n",
+        "model_3_layer = nn.Sequential(nn.Linear(D_i, D_o))\n",
+        "\n",
+        "# TODO create model with four hidden layers and 63 hidden units per layer\n",
+        "# Replace this line\n",
+        "model_4_layer = nn.Sequential(nn.Linear(D_i, D_o))\n"
+      ],
+      "metadata": {
+        "id": "FslroPJJffrh"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "# He initialization of weights\n",
+        "def weights_init(layer_in):\n",
+        "  if isinstance(layer_in, nn.Linear):\n",
+        "    nn.init.kaiming_uniform_(layer_in.weight)\n",
+        "    layer_in.bias.data.fill_(0.0)"
+      ],
+      "metadata": {
+        "id": "YgLaex1pfhqz"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "def train_model(model, train_data_x, train_data_y, n_epoch, DEVICE):\n",
+        "  print(\"This is going to take a long time!\")\n",
+        "  # choose cross entropy loss function (equation 5.24 in the loss notes)\n",
+        "  loss_function = nn.CrossEntropyLoss()\n",
+        "  # construct SGD optimizer and initialize learning rate to small value and momentum to 0\n",
+        "  optimizer = torch.optim.SGD(model.parameters(), lr = 0.0025, momentum=0.0)\n",
+        "  # create 100 dummy data points and store in data loader class\n",
+        "  x_train = torch.tensor(train_data_x.transpose(), dtype=torch.float32, device=DEVICE)\n",
+        "  y_train = torch.tensor(train_data_y, dtype=torch.long, device=DEVICE)\n",
+        "\n",
+        "  # load the data into a class that creates the batches -- full batch as there are 4000 examples\n",
+        "  data_loader = DataLoader(TensorDataset(x_train,y_train), batch_size=4000, shuffle=False, worker_init_fn=np.random.seed(1))\n",
+        "\n",
+        "  # Initialize model weights\n",
+        "  model.apply(weights_init)\n",
+        "\n",
+        "  # store the errors percentage at each point\n",
+        "  errors_train = np.zeros((n_epoch))\n",
+        "\n",
+        "  for epoch in range(n_epoch):\n",
+        "    # loop over batches\n",
+        "    for i, data in enumerate(data_loader):\n",
+        "      # retrieve inputs and labels for this batch\n",
+        "      x_batch, y_batch = data\n",
+        "      # zero the parameter gradients\n",
+        "      optimizer.zero_grad()\n",
+        "      # forward pass -- calculate model output\n",
+        "      pred = model(x_batch)\n",
+        "      # compute the loss\n",
+        "      loss = loss_function(pred, y_batch)\n",
+        "      # Store the errors\n",
+        "      _, predicted_train_class = torch.max(pred.data, 1)\n",
+        "      errors_train[epoch] = 100 - 100 * (predicted_train_class == y_train).float().sum() / len(y_train)\n",
+        "      # backward pass\n",
+        "      loss.backward()\n",
+        "      # SGD update\n",
+        "      optimizer.step()\n",
+        "\n",
+        "      if epoch % 10 == 0:\n",
+        "        clear_output(wait=True)\n",
+        "        display(\"Epoch %d, errors_train %3.3f\"%(epoch, errors_train[epoch]))\n",
+        "\n",
+        "  return errors_train"
+      ],
+      "metadata": {
+        "id": "NYw8I_3mmX5c"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "# Load in the data\n",
+        "train_data_x = data['x'].transpose()\n",
+        "train_data_y = data['y']\n",
+        "# Print out sizes\n",
+        "print(\"Train data: %d examples (columns), each of which has %d dimensions (rows)\"%((train_data_x.shape[1],train_data_x.shape[0])))"
+      ],
+      "metadata": {
+        "id": "4FE3HQ_vedXO"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "# Train the four models\n",
+        "model_4_layer = model_4_layer.to(DEVICE)\n",
+        "errors_four_layers = train_model(model_4_layer, train_data_x, train_data_y, n_epoch=200000, DEVICE=DEVICE)\n"
+      ],
+      "metadata": {
+        "id": "b56wdODqemF1"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "model_3_layer = model_3_layer.to(DEVICE)\n",
+        "errors_three_layers = train_model(model_3_layer, train_data_x, train_data_y, n_epoch=200000, DEVICE=DEVICE)\n"
+      ],
+      "metadata": {
+        "id": "63WsEgDCmbB4"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "model_2_layer = model_2_layer.to(DEVICE)\n",
+        "errors_two_layers = train_model(model_2_layer, train_data_x, train_data_y, n_epoch=200000, DEVICE=DEVICE)\n"
+      ],
+      "metadata": {
+        "id": "3TfS5DaZmdCN"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "model_1_layer = model_1_layer.to(DEVICE)\n",
+        "errors_one_layer = train_model(model_1_layer, train_data_x, train_data_y, n_epoch=500000, DEVICE=DEVICE)"
+      ],
+      "metadata": {
+        "id": "3f9Z6Mh4meeA"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "# Plot the results\n",
+        "fig, ax = plt.subplots()\n",
+        "ax.plot(errors_one_layer,'r-',label='one layer')\n",
+        "ax.plot(errors_two_layers,'g-',label='two layers')\n",
+        "ax.plot(errors_three_layers,'b-',label='three layers')\n",
+        "ax.plot(errors_four_layers,'m-',label='four layers')\n",
+        "ax.set_ylim(0,100)\n",
+        "ax.set_xlabel('Epoch'); ax.set_ylabel('Percent error')\n",
+        "ax.legend()\n",
+        "plt.show()"
+      ],
+      "metadata": {
+        "id": "pYL0YMI5oNSR"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [],
+      "metadata": {
+        "id": "iJem05Y03mZB"
+      },
+      "execution_count": null,
+      "outputs": []
+    }
+  ]
+}

Notebooks/Chap20/20_3_Lottery_Tickets.ipynb

@@ -0,0 +1,377 @@
+{
+  "nbformat": 4,
+  "nbformat_minor": 0,
+  "metadata": {
+    "colab": {
+      "provenance": [],
+      "include_colab_link": true
+    },
+    "kernelspec": {
+      "name": "python3",
+      "display_name": "Python 3"
+    }
+  },
+  "cells": [
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "view-in-github",
+        "colab_type": "text"
+      },
+      "source": [
+        "<a href=\"https://colab.research.google.com/github/udlbook/udlbook/blob/main/Notebooks/Chap20/20_3_Lottery_Tickets.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "dKUcDM76bHx3"
+      },
+      "source": [
+        "# **Notebook 20.3: Lottery tickets**\n",
+        "\n",
+        "This notebook investigates the phenomenon of lottery tickets as discussed in section 20.2.7.  This notebook is highly derivative of the MNIST-1D code hosted by Sam Greydanus at https://github.com/greydanus/mnist1d.   \n",
+        "\n",
+        "Work through the cells below, running each cell in turn. In various places you will see the words \"TO DO\". Follow the instructions at these places and make predictions about what is going to happen or write code to complete the functions.\n",
+        "\n",
+        "Contact me at udlbookmail@gmail.com if you find any mistakes or have any suggestions."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "metadata": {
+        "id": "Sg2i1QmhKW5d"
+      },
+      "source": [
+        "# Run this if you're in a Colab\n",
+        "!git clone https://github.com/greydanus/mnist1d"
+      ],
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "# Lottery tickets\n",
+        "\n",
+        "Lottery tickets were first identified by [Frankle and Carbin (2018)](https://arxiv.org/abs/1803.03635).  They noted that after training a network, they could set the smaller weights to zero and clamp them there and retrain to get a network that was sparser (had fewer parameters) but could actually perform better.  So within the neural network there lie smaller sub-networks which are superior.  If we knew what these were, we could train them from scratch, but there is currently no way of finding out."
+      ],
+      "metadata": {
+        "id": "97g8gY5XdcKR"
+      }
+    },
+    {
+      "cell_type": "code",
+      "metadata": {
+        "id": "KaQo7QhvXvid"
+      },
+      "source": [
+        "import numpy as np\n",
+        "import matplotlib.pyplot as plt\n",
+        "\n",
+        "import torch\n",
+        "import torch.nn as nn\n",
+        "import torch.nn.functional as F\n",
+        "import torch.optim as optim\n",
+        "\n",
+        "import mnist1d\n",
+        "import copy"
+      ],
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "nre26wEOfZsM"
+      },
+      "source": [
+        "## Get the MNIST1D dataset"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "metadata": {
+        "id": "I-vm_gh5xTJs"
+      },
+      "source": [
+        "args = mnist1d.get_dataset_args()\n",
+        "data = mnist1d.get_dataset(args=args)  # by default, this will download a pre-made dataset from the GitHub repo\n",
+        "\n",
+        "print(\"Examples in training set: {}\".format(len(data['y'])))\n",
+        "print(\"Examples in test set: {}\".format(len(data['y_test'])))\n",
+        "print(\"Length of each input: {}\".format(data['x'].shape[-1]))\n",
+        "print(\"Number of classes: {}\".format(len(data['templates']['y'])))"
+      ],
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "O2vy0FKjfDwr"
+      },
+      "source": [
+        "## Make an MLP that can be masked\n",
+        "These parameter-wise binary masks are how we will represent sparsity in this project. There's not a great PyTorch API for this yet, so here's a temporary solution."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "metadata": {
+        "id": "uBx5gNW-mqH_"
+      },
+      "source": [
+        "# Class to represent linear layer where some of the weights are forced to zero.\n",
+        "class SparseLinear(torch.nn.Module):\n",
+        "  def __init__(self, x_size, y_size):\n",
+        "    super(SparseLinear, self).__init__()\n",
+        "    self.linear = torch.nn.Linear(x_size, y_size)\n",
+        "    param_vec = torch.cat([p.flatten() for p in self.parameters()])\n",
+        "    self.mask = torch.ones_like(param_vec)\n",
+        "\n",
+        "  def forward(self, x, apply_mask=True):\n",
+        "    if apply_mask:\n",
+        "      self.apply_mask()\n",
+        "    return self.linear(x)\n",
+        "\n",
+        "  def update_mask(self, new_mask):\n",
+        "    self.mask = new_mask\n",
+        "    self.apply_mask()\n",
+        "\n",
+        "  def apply_mask(self):\n",
+        "    self.vec2param(self.param2vec())\n",
+        "\n",
+        "  def param2vec(self):\n",
+        "    vec = torch.cat([p.flatten() for p in self.parameters()])\n",
+        "    return self.mask * vec\n",
+        "\n",
+        "  def vec2param(self, vec):\n",
+        "    pointer = 0\n",
+        "    for param in self.parameters():\n",
+        "      param_len = np.cumprod(param.shape)[-1]\n",
+        "      new_param = vec[pointer:pointer+param_len].reshape(param.shape)\n",
+        "      param.data = new_param.data\n",
+        "      pointer += param_len\n",
+        "\n",
+        "# A two layer residual network where the linear layers are sparse\n",
+        "class SparseMLP(torch.nn.Module):\n",
+        "  def __init__(self, input_size, output_size, hidden_size=100):\n",
+        "    super(SparseMLP, self).__init__()\n",
+        "    self.linear1 = SparseLinear(input_size, hidden_size)\n",
+        "    self.linear2 = SparseLinear(hidden_size, hidden_size)\n",
+        "    self.linear3 = SparseLinear(hidden_size, output_size)\n",
+        "    self.layers = [self.linear1, self.linear2, self.linear3]\n",
+        "\n",
+        "  def forward(self, x):\n",
+        "    h = torch.relu(self.linear1(x))\n",
+        "    h = h + torch.relu(self.linear2(h))\n",
+        "    h = self.linear3(h)\n",
+        "    return h\n",
+        "\n",
+        "  def get_layer_masks(self):\n",
+        "    return [l.mask for l in self.layers]\n",
+        "\n",
+        "  def set_layer_masks(self, new_masks):\n",
+        "    for i, l in enumerate(self.layers):\n",
+        "      l.update_mask(new_masks[i])\n",
+        "\n",
+        "  def get_layer_vecs(self):\n",
+        "    return [l.param2vec() for l in self.layers]\n",
+        "\n",
+        "  def set_layer_vecs(self, vecs):\n",
+        "    for i, l in enumerate(self.layers):\n",
+        "      l.vec2param(vecs[i])"
+      ],
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "2hwmH2vIbHin"
+      },
+      "source": [
+        "Now we need a routine that takes the weights from the model and returns a mask that identifies the positions with the lowest magnitude.  These will be the weights that we mask."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "metadata": {
+        "id": "Md2F9WDgYSqT"
+      },
+      "source": [
+        "# absolute weights -- absolute values of all the weights from the model in a long vector\n",
+        "# percent_sparse: how much to sparsify the model\n",
+        "def get_mask(absolute_weights, percent_sparse):\n",
+        "  # TODO -- Write a function that returns a mask that has a zero\n",
+        "  # everywhere for the lowest \"percent_sparse\" of the absolute weights.\n",
+        "  # E.g. if absolute_weights contains [5,6,0,1,7] and we want percent_sparse of 40%,\n",
+        "  # we would return [1,1,0,0,1]\n",
+        "  # Remember that these are torch tensors and not numpy arrays\n",
+        "  # Replace this function:\n",
+        "  mask = torch.ones_like(scores)\n",
+        "\n",
+        "\n",
+        "  return mask"
+      ],
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "z0McGMV-a3Xo"
+      },
+      "source": [
+        "## The prune-and-retrain cycle\n",
+        "This is the core method for finding a lottery ticket. We train a model for a fixed number of epochs, prune it, and then re-train and re-prune. We repeat this cycle until we achieve the desired level of sparsity."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "metadata": {
+        "id": "5idcbyA3Ylz_"
+      },
+      "source": [
+        "def find_lottery_ticket(model, dataset, args, sparsity_schedule, criteria_fn=None, **kwargs):\n",
+        "\n",
+        "  criteria_fn = lambda init_params, final_params: final_params.abs()\n",
+        "\n",
+        "  init_params = model.get_layer_vecs()\n",
+        "  stats = {'train_losses':[], 'test_losses':[], 'train_accs':[], 'test_accs':[]}\n",
+        "  models = []\n",
+        "  for i, percent_sparse in enumerate(sparsity_schedule):\n",
+        "\n",
+        "    # layer-wise pruning, where pruning heuristic is determined by criteria_fn\n",
+        "    final_params = model.get_layer_vecs()\n",
+        "    scores = [criteria_fn(ip, fp) for ip, fp in zip(init_params, final_params)]\n",
+        "    masks = [get_mask(s, percent_sparse) for s in scores]\n",
+        "\n",
+        "    # update model with mask and init parameters\n",
+        "    model.set_layer_vecs(init_params)\n",
+        "    model.set_layer_masks(masks)\n",
+        "\n",
+        "    # training process\n",
+        "    results = mnist1d.train_model(dataset, model, args)\n",
+        "    model = results['checkpoints'][-1]\n",
+        "\n",
+        "    # store stats\n",
+        "    stats['train_losses'].append(results['train_losses'])\n",
+        "    stats['test_losses'].append(results['test_losses'])\n",
+        "    stats['train_accs'].append(results['train_acc'])\n",
+        "    stats['test_accs'].append(results['test_acc'])\n",
+        "\n",
+        "    # print progress\n",
+        "    if (i+1) % 1 == 0:\n",
+        "      print('\\tretrain #{}, sparsity {:.2f}, final_train_loss {:.3e}, max_acc {:.1f}, last_acc {:.1f}, mean_acc {:.1f}'\n",
+        "            .format(i+1, percent_sparse, results['train_losses'][-1], np.max(results['test_acc']),\n",
+        "            results['test_acc'][-1], np.mean(results['test_acc']) ))\n",
+        "      models.append(copy.deepcopy(model))\n",
+        "\n",
+        "  stats = {k: np.stack(v) for k, v in stats.items()}\n",
+        "  return models, stats"
+      ],
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "m4lokvdD4DKI"
+      },
+      "source": [
+        "## Choose hyperparameters"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "metadata": {
+        "id": "OUe7-b-7Yl2c"
+      },
+      "source": [
+        "# train settings\n",
+        "model_args = mnist1d.get_model_args()\n",
+        "model_args.total_steps = 1501\n",
+        "model_args.hidden_size = 500\n",
+        "model_args.print_every = 5000 # print never\n",
+        "model_args.eval_every = 100\n",
+        "model_args.learning_rate = 2e-2\n",
+        "model_args.device = str('cpu')"
+      ],
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "hVgDM5rI4J65"
+      },
+      "source": [
+        "Find the lottery ticket by repeatedly training and then pruning weights based on their magnitudes. We'll remove 1% of the weights each time. This is going to take half an hour or so.  Go and have lunch or whatever."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "# sparsity settings - we will train 100 models with progressively increasing sparsity\n",
+        "num_retrains = 100\n",
+        "sparsity_schedule = np.linspace(0,1.,num_retrains)\n",
+        "\n",
+        "print(\"Magnitude pruning\")\n",
+        "mnist1d.set_seed(model_args.seed)\n",
+        "model = SparseMLP(model_args.input_size, model_args.output_size, hidden_size=model_args.hidden_size)\n",
+        "\n",
+        "criteria_fn = lambda init_params, final_params: final_params.abs()\n",
+        "lott_models, lott_stats = find_lottery_ticket(model, data, model_args, sparsity_schedule, criteria_fn=criteria_fn, prune_print_every=1)"
+      ],
+      "metadata": {
+        "id": "M25YpCuS1Gn0"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "test_losses = lott_stats['test_losses'][:,-1]\n",
+        "test_accs = lott_stats['test_accs'][:,-1]\n",
+        "\n",
+        "fig,ax = plt.subplots()\n",
+        "ax.plot(sparsity_schedule, test_losses,'r-')\n",
+        "ax.plot((sparsity_schedule[0], sparsity_schedule[-1]),(test_losses[0], test_losses[0]),'k--',label='dense')\n",
+        "ax.set_xlabel('Sparsity')\n",
+        "ax.set_ylabel('Loss')\n",
+        "ax.set_xlim(0,1)\n",
+        "ax.legend()\n",
+        "plt.show()\n",
+        "\n",
+        "fig,ax = plt.subplots()\n",
+        "ax.plot(sparsity_schedule, 100-test_accs,'r-')\n",
+        "ax.plot((sparsity_schedule[0], sparsity_schedule[-1]),(100-test_accs[0], 100-test_accs[0]),'k--',label='dense')\n",
+        "ax.set_xlabel('Sparsity')\n",
+        "ax.set_ylabel('Percent Error')\n",
+        "ax.set_xlim(0,1)\n",
+        "ax.set_ylim(0,100)\n",
+        "ax.legend()\n",
+        "plt.show()\n"
+      ],
+      "metadata": {
+        "id": "TCs-kt6-3xHB"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "You should see that the test loss decreases and the errors decrease with more as the network gets sparser.  The dashed line represents the original dense (unpruned) network.  We have identified a simpler network that was \"inside\" the original network for which the results are superior.  Of course if we make it too sparse, then it gets worse again.\n",
+        "\n",
+        "This phenomenon is explored much further in the original notebook by Sam Greydanus which can be found [here](https://github.com/greydanus/mnist1d)."
+      ],
+      "metadata": {
+        "id": "CEj5_ZEHcRpw"
+      }
+    }
+  ]
+}

Notebooks/Chap20/20_4_Adversarial_Attacks.ipynb

@@ -0,0 +1,386 @@
+{
+  "nbformat": 4,
+  "nbformat_minor": 0,
+  "metadata": {
+    "colab": {
+      "provenance": [],
+      "authorship_tag": "ABX9TyP9amtzXsNWqkmiPUQgxzKV",
+      "include_colab_link": true
+    },
+    "kernelspec": {
+      "name": "python3",
+      "display_name": "Python 3"
+    },
+    "language_info": {
+      "name": "python"
+    }
+  },
+  "cells": [
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "view-in-github",
+        "colab_type": "text"
+      },
+      "source": [
+        "<a href=\"https://colab.research.google.com/github/udlbook/udlbook/blob/main/Notebooks/Chap20/20_4_Adversarial_Attacks.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "# **Notebook 20.4: Adversarial attacks**\n",
+        "\n",
+        "This notebook builds uses the network for classification of MNIST from Notebook 10.5.  The code is adapted from https://nextjournal.com/gkoehler/pytorch-mnist, and uses the fast gradient sign attack of [Goodfellow et al. (2015)](https://arxiv.org/abs/1412.6572).  Having trained, the network, we search for adversarial examples -- inputs which look very similar to class A, but are mistakenly classified as class B.  We do this by starting with a correctly classified example and perturbing it according to the gradients of the network so that the output changes.\n",
+        "\n",
+        "Work through the cells below, running each cell in turn. In various places you will see the words \"TO DO\". Follow the instructions at these places and make predictions about what is going to happen or write code to complete the functions.\n",
+        "\n",
+        "Contact me at udlbookmail@gmail.com if you find any mistakes or have any suggestions.\n"
+      ],
+      "metadata": {
+        "id": "t9vk9Elugvmi"
+      }
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "import torch\n",
+        "import torchvision\n",
+        "import torch.nn as nn\n",
+        "import torch.nn.functional as F\n",
+        "import torch.optim as optim\n",
+        "import matplotlib.pyplot as plt\n",
+        "import random"
+      ],
+      "metadata": {
+        "id": "YrXWAH7sUWvU"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "# Run this once to load the train and test data straight into a dataloader class\n",
+        "# that will provide the batches\n",
+        "batch_size_train = 64\n",
+        "batch_size_test = 1000\n",
+        "train_loader = torch.utils.data.DataLoader(\n",
+        "  torchvision.datasets.MNIST('/files/', train=True, download=True,\n",
+        "                             transform=torchvision.transforms.Compose([\n",
+        "                               torchvision.transforms.ToTensor(),\n",
+        "                               torchvision.transforms.Normalize(\n",
+        "                                 (0.1307,), (0.3081,))\n",
+        "                             ])),\n",
+        "  batch_size=batch_size_train, shuffle=True)\n",
+        "\n",
+        "test_loader = torch.utils.data.DataLoader(\n",
+        "  torchvision.datasets.MNIST('/files/', train=False, download=True,\n",
+        "                             transform=torchvision.transforms.Compose([\n",
+        "                               torchvision.transforms.ToTensor(),\n",
+        "                               torchvision.transforms.Normalize(\n",
+        "                                 (0.1307,), (0.3081,))\n",
+        "                             ])),\n",
+        "  batch_size=batch_size_test, shuffle=True)"
+      ],
+      "metadata": {
+        "id": "wScBGXXFVadm"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "# Let's draw some of the training data\n",
+        "examples = enumerate(test_loader)\n",
+        "batch_idx, (example_data, example_targets) = next(examples)\n",
+        "\n",
+        "fig = plt.figure()\n",
+        "for i in range(6):\n",
+        "  plt.subplot(2,3,i+1)\n",
+        "  plt.tight_layout()\n",
+        "  plt.imshow(example_data[i][0], cmap='gray', interpolation='none')\n",
+        "  plt.title(\"Ground Truth: {}\".format(example_targets[i]))\n",
+        "  plt.xticks([])\n",
+        "  plt.yticks([])\n",
+        "plt.show()"
+      ],
+      "metadata": {
+        "id": "8bKADvLHbiV5"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "Define the network.  This is a more typical way to define a network than the sequential structure.  We define a class for the network, and define the parameters in the constructor.  Then we use a function called forward to actually run the network.  It's easy to see how you might use residual connections in this format."
+      ],
+      "metadata": {
+        "id": "_sFvRDGrl4qe"
+      }
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "from os import X_OK\n",
+        "\n",
+        "class Net(nn.Module):\n",
+        "    def __init__(self):\n",
+        "        super(Net, self).__init__()\n",
+        "        self.conv1 = nn.Conv2d(1, 10, kernel_size=5)\n",
+        "        self.conv2 = nn.Conv2d(10, 20, kernel_size=5)\n",
+        "        self.drop = nn.Dropout2d()\n",
+        "        self.fc1 = nn.Linear(320, 50)\n",
+        "        self.fc2 = nn.Linear(50, 10)\n",
+        "\n",
+        "    def forward(self, x):\n",
+        "        x = self.conv1(x)\n",
+        "        x = F.max_pool2d(x,2)\n",
+        "        x = F.relu(x)\n",
+        "        x = self.conv2(x)\n",
+        "        x = self.drop(x)\n",
+        "        x = F.max_pool2d(x,2)\n",
+        "        x = F.relu(x)\n",
+        "        x = x.flatten(1)\n",
+        "        x = F.relu(self.fc1(x))\n",
+        "        x = self.fc2(x)\n",
+        "        x = F.log_softmax(x)\n",
+        "        return x"
+      ],
+      "metadata": {
+        "id": "EQkvw2KOPVl7"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "# He initialization of weights\n",
+        "def weights_init(layer_in):\n",
+        "  if isinstance(layer_in, nn.Linear):\n",
+        "    nn.init.kaiming_uniform_(layer_in.weight)\n",
+        "    layer_in.bias.data.fill_(0.0)"
+      ],
+      "metadata": {
+        "id": "qWZtkCZcU_dg"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "# Create network\n",
+        "model = Net()\n",
+        "# Initialize model weights\n",
+        "model.apply(weights_init)\n",
+        "# Define optimizer\n",
+        "optimizer = optim.SGD(model.parameters(), lr=0.01, momentum=0.5)"
+      ],
+      "metadata": {
+        "id": "FslroPJJffrh"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "# Main training routine\n",
+        "def train(epoch):\n",
+        "  model.train()\n",
+        "  # Get each\n",
+        "  for batch_idx, (data, target) in enumerate(train_loader):\n",
+        "    optimizer.zero_grad()\n",
+        "    output = model(data)\n",
+        "    loss = F.nll_loss(output, target)\n",
+        "    loss.backward()\n",
+        "    optimizer.step()\n",
+        "    # Store results\n",
+        "    if batch_idx % 10 == 0:\n",
+        "      print('Train Epoch: {} [{}/{}]\\tLoss: {:.6f}'.format(\n",
+        "        epoch, batch_idx * len(data), len(train_loader.dataset), loss.item()))"
+      ],
+      "metadata": {
+        "id": "xKQd9PzkQ766"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "# Run on test data\n",
+        "def test():\n",
+        "  model.eval()\n",
+        "  test_loss = 0\n",
+        "  correct = 0\n",
+        "  with torch.no_grad():\n",
+        "    for data, target in test_loader:\n",
+        "      output = model(data)\n",
+        "      test_loss += F.nll_loss(output, target, size_average=False).item()\n",
+        "      pred = output.data.max(1, keepdim=True)[1]\n",
+        "      correct += pred.eq(target.data.view_as(pred)).sum()\n",
+        "  test_loss /= len(test_loader.dataset)\n",
+        "  print('\\nTest set: Avg. loss: {:.4f}, Accuracy: {}/{} ({:.0f}%)\\n'.format(\n",
+        "    test_loss, correct, len(test_loader.dataset),\n",
+        "    100. * correct / len(test_loader.dataset)))"
+      ],
+      "metadata": {
+        "id": "Byn-f7qWRLxX"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "# Get initial performance\n",
+        "test()\n",
+        "# Train for three epochs\n",
+        "n_epochs = 3\n",
+        "for epoch in range(1, n_epochs + 1):\n",
+        "  train(epoch)\n",
+        "  test()"
+      ],
+      "metadata": {
+        "id": "YgLaex1pfhqz"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "# Run network on data we got before and show predictions\n",
+        "output = model(example_data)\n",
+        "\n",
+        "fig = plt.figure()\n",
+        "for i in range(6):\n",
+        "  plt.subplot(2,3,i+1)\n",
+        "  plt.tight_layout()\n",
+        "  plt.imshow(example_data[i][0], cmap='gray', interpolation='none')\n",
+        "  plt.title(\"Prediction: {}\".format(\n",
+        "    output.data.max(1, keepdim=True)[1][i].item()))\n",
+        "  plt.xticks([])\n",
+        "  plt.yticks([])\n",
+        "plt.show()"
+      ],
+      "metadata": {
+        "id": "o7fRUAy9Se1B"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "This is the code that does the adversarial attack. It is adapted from [here](https://pytorch.org/tutorials/beginner/fgsm_tutorial.html).   It is an example of the fast gradient sign method (FGSM), which modifies the data by\n",
+        "\n",
+        "\n",
+        "\n",
+        "*   Calculating the derivative $\\partial L/\\partial \\mathbf{x}$ of the loss $L$ with respect to the input data $\\mathbf{x}$.\n",
+        "*   Finds the sign of the gradient at each point (making a tensor the same size as $\\mathbf{x}$ with a one where it was positive and minus one where it was negative.  \n",
+        "*   Multiplying this vector by $\\epsilon$ and adding it back to the original data\n",
+        "\n",
+        "\n"
+      ],
+      "metadata": {
+        "id": "EabuoMdP32Hd"
+      }
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "# FGSM attack code.\n",
+        "def fgsm_attack(x, epsilon, dLdx):\n",
+        "    # TODO -- write this function\n",
+        "    # Get the sign of the gradient\n",
+        "    # Add epsilon times the size of gradient to x\n",
+        "    # Replace this line\n",
+        "    x_modified = torch.zeros_like(x)\n",
+        "\n",
+        "    # Return the perturbed image\n",
+        "    return x_modified"
+      ],
+      "metadata": {
+        "id": "gAX7tnld46q1"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "no_examples = 3\n",
+        "epsilon = 0.5\n",
+        "for i in range(no_examples):\n",
+        "  # Reset gradients\n",
+        "  optimizer.zero_grad()\n",
+        "\n",
+        "  # Get the i'th data example\n",
+        "  x = example_data[i,:,:,:]\n",
+        "  # Add an extra dimension back to the beginning\n",
+        "  x= x[None, :,:,:]\n",
+        "  x.requires_grad = True\n",
+        "  # Get the i'th target\n",
+        "  y = torch.ones(1, dtype=torch.long) * example_targets[i]\n",
+        "\n",
+        "  # Run the model\n",
+        "  output = model(x)\n",
+        "  # Compute the loss\n",
+        "  loss = F.nll_loss(output, y)\n",
+        "  # Back propagate\n",
+        "  loss.backward()\n",
+        "\n",
+        "  # Collect ``datagrad``\n",
+        "  dLdx = x.grad.data\n",
+        "\n",
+        "  # Call FGSM Attack\n",
+        "  x_prime = fgsm_attack(x, epsilon, dLdx)\n",
+        "\n",
+        "  # Re-classify the perturbed image\n",
+        "  output_prime = model(x_prime)\n",
+        "\n",
+        "  x = x.detach().numpy()\n",
+        "  fig = plt.figure()\n",
+        "  plt.subplot(1,2,1)\n",
+        "  plt.tight_layout()\n",
+        "  plt.imshow(x[0][0], cmap='gray', interpolation='none')\n",
+        "  plt.title(\"Original Prediction: {}\".format(\n",
+        "    output.data.max(1, keepdim=True)[1][0].item()))\n",
+        "  plt.xticks([])\n",
+        "  plt.yticks([])\n",
+        "\n",
+        "  plt.subplot(1,2,2)\n",
+        "  plt.tight_layout()\n",
+        "  plt.imshow(x_prime[0][0].detach().numpy(), cmap='gray', interpolation='none')\n",
+        "  plt.title(\"Perturbed Prediction: {}\".format(\n",
+        "    output_prime.data.max(1, keepdim=True)[1][0].item()))\n",
+        "  plt.xticks([])\n",
+        "  plt.yticks([])\n",
+        "\n",
+        "plt.show()"
+      ],
+      "metadata": {
+        "id": "AuNTYWboufbm"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "Although we have only added a small amount of noise, the model is fooled into thinking that these images come from a different class.\n",
+        "\n",
+        "TODO -- Modify the attack so that it iteratively perturbs the data. i.e., so we take a small step epsilon, then re-calculate the gradient and take another small step according to the new gradient signs."
+      ],
+      "metadata": {
+        "id": "vFXWK826HPQ8"
+      }
+    }
+  ]
+}

Notebooks/Chap21/21_1_Bias_Mitigation.ipynb

@@ -0,0 +1,457 @@
+{
+  "cells": [
+    {
+      "attachments": {},
+      "cell_type": "markdown",
+      "metadata": {
+        "colab_type": "text",
+        "id": "view-in-github"
+      },
+      "source": [
+        "<a href=\"https://colab.research.google.com/github/udlbook/udlbook/blob/main/Notebooks/Chap21/21_1_Bias_Mitigation.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
+      ]
+    },
+    {
+      "attachments": {},
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "t9vk9Elugvmi"
+      },
+      "source": [
+        "# **Notebook 21.1: Bias mitigation**\n",
+        "\n",
+        "This notebook investigates a post-processing method for bias mitigation (see figure 21.2 in the book). It based on this [blog](https://www.borealisai.com/research-blogs/tutorial1-bias-and-fairness-ai/) that I wrote for Borealis AI in 2019, which itself was derived from [this blog](https://research.google.com/bigpicture/attacking-discrimination-in-ml/) by Wattenberg, Viégas, and Hardt.\n",
+        "\n",
+        "Work through the cells below, running each cell in turn. In various places you will see the words \"TO DO\". Follow the instructions at these places and make predictions about what is going to happen or write code to complete the functions.\n",
+        "\n",
+        "Contact me at udlbookmail@gmail.com if you find any mistakes or have any suggestions.\n"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "yC_LpiJqZXEL"
+      },
+      "outputs": [],
+      "source": [
+        "import numpy as np\n",
+        "import matplotlib.pyplot as plt"
+      ]
+    },
+    {
+      "attachments": {},
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "2FYo1dWGZXgg"
+      },
+      "source": [
+        "# Worked example: loans\n",
+        "\n",
+        "Consider the example of an algorithm $c=\\text{f}[\\mathbf{x},\\boldsymbol\\phi]$ that predicts credit rating scores $c$ for loan decisions.  There are two pools of loan applicants identified by the variable $p\\in\\{0,1\\}$ that we’ll describe as the blue and yellow populations. We assume that we are given historical data, so we know both the credit rating and whether the applicant actually defaulted on the loan ($y=0$) or\n",
+        " repaid it ($y=1$).\n",
+        "\n",
+        "We can now think of four groups of data corresponding to (i) the blue and yellow populations and (ii) whether they did or did not repay the loan. For each of these four groups we have a distribution of credit ratings (figure 1). In an ideal world, the two distributions for the yellow population would be exactly the same as those for the blue population. However, as figure 1 shows, this is clearly not the case here."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "O_0gGH9hZcjo"
+      },
+      "outputs": [],
+      "source": [
+        "# Class that can describe interesting curve shapes based on the input parameters\n",
+        "# Details don't matter\n",
+        "class FreqCurve:\n",
+        "  def __init__(self, weight, mean1, mean2, sigma1, sigma2, prop):\n",
+        "    self.mean1 = mean1\n",
+        "    self.mean2 = mean2\n",
+        "    self.sigma1 = sigma1\n",
+        "    self.sigma2 = sigma2\n",
+        "    self.prop = prop\n",
+        "    self.weight = weight\n",
+        "\n",
+        "  def freq(self, x):\n",
+        "    return self.weight * self.prop * np.exp(-0.5 * (x-self.mean1) * (x-self.mean1) / (self.sigma1 * self.sigma1)) \\\n",
+        "                * 1.0 / np.sqrt(2*np.pi*self.sigma1*self.sigma1) \\\n",
+        "          + self.weight * (1-self.prop) * np.exp(-0.5 * (x-self.mean2) * (x-self.mean2) / (self.sigma2 * self.sigma2)) \\\n",
+        "                * 1.0 / np.sqrt(2*np.pi*self.sigma2*self.sigma2)\n"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "Bkp7vffBbrNW"
+      },
+      "outputs": [],
+      "source": [
+        "credit_scores = np.arange(-4,4,0.01)\n",
+        "freq_y0_p0 = FreqCurve(800, -1.5, -2.5, 0.8, 0.6, 0.6).freq(credit_scores)\n",
+        "freq_y1_p0 = FreqCurve(500, 0.1, 0.7, 1.5, 0.8, 0.4 ).freq(credit_scores)\n",
+        "freq_y0_p1 = FreqCurve(400, 0.2, -0.1, 0.8, 0.6, 0.3).freq(credit_scores)\n",
+        "freq_y1_p1 = FreqCurve(650, 0.6, 1.6, 1.2, 0.7, 0.6 ).freq(credit_scores)\n"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "Jf7uqyRyhVdS"
+      },
+      "outputs": [],
+      "source": [
+        "\n",
+        "fig = plt.figure\n",
+        "ax = plt.subplot(2,2,1)\n",
+        "plt.tight_layout()\n",
+        "ax.plot(credit_scores, freq_y0_p0, 'b--', label='y=0 (defaulted)')\n",
+        "ax.plot(credit_scores, freq_y1_p0, 'b-', label='y=1 (repaid)')\n",
+        "ax.set_xlim(-4,4)\n",
+        "ax.set_ylim(0,500)\n",
+        "ax.set_xlabel('Credit score, $c$')\n",
+        "ax.set_ylabel('Frequency')\n",
+        "ax.set_title('Population p=0')\n",
+        "ax.legend()\n",
+        "\n",
+        "ax = plt.subplot(2,2,2)\n",
+        "plt.tight_layout()\n",
+        "ax.plot(credit_scores, freq_y0_p1, 'y--', label='y=0 (defaulted)')\n",
+        "ax.plot(credit_scores, freq_y1_p1, 'y-', label='y=1 (repaid)')\n",
+        "ax.set_xlim(-4,4)\n",
+        "ax.set_ylim(0,500)\n",
+        "ax.set_xlabel('Credit score, $c$')\n",
+        "ax.set_ylabel('Frequency')\n",
+        "ax.set_title('Population p=1')\n",
+        "ax.legend()\n",
+        "\n",
+        "plt.show()"
+      ]
+    },
+    {
+      "attachments": {},
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "CfZ-srQtmff2"
+      },
+      "source": [
+        "Why might the distributions for blue and yellow populations be different? It could be that the behaviour of the populations is identical, but the credit rating algorithm is biased; it may favor one population over another or simply be more noisy for one group. Alternatively, it could be that that the populations genuinely behave differently. In practice, the differences in blue and yellow distributions are probably attributable to a combination of these factors.\n",
+        "\n",
+        "Let’s assume that we can’t retrain the credit score prediction algorithm; our job is to adjudicate whether each individual is refused the loan ($\\hat{y}=0$)\n",
+        " or granted it ($\\hat{y}=1$). Since we only have the credit score\n",
+        " to go on, the best we can do is to assign different thresholds $\\tau_{1}$\n",
+        " and $\\tau_{2}$\n",
+        " for the blue and yellow populations so that the loan is granted if the credit score $c$ generated by the model exceeds $\\tau_0$ for the blue population and $\\tau_1$ for the yellow population."
+      ]
+    },
+    {
+      "attachments": {},
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "569oU1OtoFz8"
+      },
+      "source": [
+        "Now let's investiate how to set these thresholds to fulfil different criteria."
+      ]
+    },
+    {
+      "attachments": {},
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "bE7yPyuWoSUy"
+      },
+      "source": [
+        "# Blindness to protected attribute\n",
+        "\n",
+        "We'll first do the simplest possible thing.  We'll choose the same threshold for both blue and yellow populations so that $\\tau_0$ = $\\tau_1$.  Basically, we'll ignore what we know about the group membership.  Let's see what the ramifications of that."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "WIG8I-LvoFBY"
+      },
+      "outputs": [],
+      "source": [
+        "# Set the thresholds\n",
+        "tau0 = tau1 = 0.0"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "2EvkCvVBiCBn"
+      },
+      "outputs": [],
+      "source": [
+        "def compute_probability_get_loan(credit_scores, frequencies, threshold):\n",
+        "  # TODO - Write this function\n",
+        "  # Return the probability that someone from this group loan based on the frequencies of each\n",
+        "  # credit score for this group\n",
+        "  # Replace this line:\n",
+        "  prob = 0.5\n",
+        "\n",
+        "\n",
+        "  return prob"
+      ]
+    },
+    {
+      "attachments": {},
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "AGT40q6_qfpv"
+      },
+      "source": [
+        "First let's see what the overall probability of getting the loan is for the yellow and blue populations."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "4nI-PR_wqWj6"
+      },
+      "outputs": [],
+      "source": [
+        "pr_get_loan_p0 = compute_probability_get_loan(credit_scores, freq_y0_p0+freq_y1_p0, tau0)\n",
+        "pr_get_loan_p1 = compute_probability_get_loan(credit_scores, freq_y0_p1+freq_y1_p1, tau1)\n",
+        "print(\"Probability blue group gets loan = %3.3f\"%(pr_get_loan_p0))\n",
+        "print(\"Probability yellow group gets loan = %3.3f\"%(pr_get_loan_p1))"
+      ]
+    },
+    {
+      "attachments": {},
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "G2pEa6h6sIyu"
+      },
+      "source": [
+        "Now let's plot a receiver operating characteristic (ROC) curve.  This shows the rate of true positives $Pr(\\hat{y}=1|y=1)$ (people who got loan and paid it back) and false alarms $Pr(\\hat{y}=1|y=0)$ (people who got the loan but didn't pay it back) for all possible thresholds."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "2C7kNt3hqwiu"
+      },
+      "outputs": [],
+      "source": [
+        "def plot_roc(credit_scores, freq_y0_p0, freq_y1_p0, freq_y0_p1, freq_y1_p1, tau0, tau1):\n",
+        "  true_positives_p0 = np.zeros_like(credit_scores)\n",
+        "  false_alarms_p0 = np.zeros_like(credit_scores)\n",
+        "  true_positives_p1 = np.zeros_like(credit_scores)\n",
+        "  false_alarms_p1 = np.zeros_like(credit_scores)\n",
+        "  for i in range(len(credit_scores)):\n",
+        "    true_positives_p0[i] = compute_probability_get_loan(credit_scores, freq_y1_p0, credit_scores[i])\n",
+        "    true_positives_p1[i] = compute_probability_get_loan(credit_scores, freq_y1_p1, credit_scores[i])\n",
+        "    false_alarms_p0[i] = compute_probability_get_loan(credit_scores, freq_y0_p0, credit_scores[i])\n",
+        "    false_alarms_p1[i] = compute_probability_get_loan(credit_scores, freq_y0_p1, credit_scores[i])\n",
+        "\n",
+        "  true_positives_p0_tau0 = compute_probability_get_loan(credit_scores, freq_y1_p0, tau0)\n",
+        "  true_positives_p1_tau1 = compute_probability_get_loan(credit_scores, freq_y1_p1, tau1)\n",
+        "  false_alarms_p0_tau0 = compute_probability_get_loan(credit_scores, freq_y0_p0, tau0)\n",
+        "  false_alarms_p1_tau1 = compute_probability_get_loan(credit_scores, freq_y0_p1, tau1)\n",
+        "\n",
+        "  fig, ax = plt.subplots()\n",
+        "  ax.plot(false_alarms_p0, true_positives_p0, 'b-')\n",
+        "  ax.plot(false_alarms_p1, true_positives_p1, 'y-')\n",
+        "  ax.plot(false_alarms_p0_tau0, true_positives_p0_tau0,'bo')\n",
+        "  ax.plot(false_alarms_p1_tau1, true_positives_p1_tau1,'yo')\n",
+        "  ax.set_xlim(0,1)\n",
+        "  ax.set_ylim(0,1)\n",
+        "  ax.set_xlabel('False alarms $Pr(\\hat{y}=1|y=0)$')\n",
+        "  ax.set_ylabel('True positives $Pr(\\hat{y}=1|y=1)$')\n",
+        "  ax.set_aspect('equal')\n",
+        "\n",
+        "  plt.show()"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "h3OOQeTsv8uS"
+      },
+      "outputs": [],
+      "source": [
+        "plot_roc(credit_scores, freq_y0_p0, freq_y1_p0, freq_y0_p1, freq_y1_p1, tau0, tau1)"
+      ]
+    },
+    {
+      "attachments": {},
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "UCObTsa57uuC"
+      },
+      "source": [
+        "On this plot, the true positive and false alarm rate for the particular thresholds ($\\tau_0=\\tau_{1}=0$) that we chose are indicated by the circles.\n",
+        "\n",
+        "This criterion is clearly not great.  The blue and yellow groups get given loans at different rates overall, and (for this threshold), the false alarms and true positives are also different, so it's not even fair when we consider whether the loans really were paid back.  \n",
+        "\n",
+        "TODO -- investigate setting a different threshold $\\tau_{0}=\\tau_{1}$.  Is it possible to make the overall rates that loans are given the same?  Is it possible to make the false alarm rates the same?  Is it possible to make the true positive rates the same?"
+      ]
+    },
+    {
+      "attachments": {},
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "Yhrxv5AQ-PWA"
+      },
+      "source": [
+        "# Equality of odds\n",
+        "\n",
+        "This definition of fairness proposes that the false positive and true positive rates should be the same for both populations. This also sounds reasonable, but the ROC curve shows that it is not possible for this example. There is no combination of thresholds that can achieve this because the ROC curves do not intersect. Even if they did, we would be stuck giving loans based on the particular false positive and true positive rates at the intersection which might not be desirable."
+      ]
+    },
+    {
+      "attachments": {},
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "l6yb8vjX-gdi"
+      },
+      "source": [
+        "Demographic parity\n",
+        "\n",
+        "The thresholds can be chosen so that the same proportion of each group are classified as $\\hat{y}=1$ and given loans. We make an equal number of loans to each group despite the different tendencies of each to repay. This has the disadvantage that the true positive and false positive rates might be completely different in different populations. From the perspective of the lender, it is desirable to give loans in proportion to people’s ability to pay them back. From the perspective of an individual in a more reliable group, it may seem unfair that the other group gets offered the same number of loans despite the fact they are less reliable."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "syjZ2fn5wC9-"
+      },
+      "outputs": [],
+      "source": [
+        "# TO DO -- try to change the two thresholds so the overall probability of getting the loan is 0.6 for each group\n",
+        "# Change the values in these lines\n",
+        "tau0 = 0.3\n",
+        "tau1 = -0.1\n",
+        "\n",
+        "\n",
+        "\n",
+        "# Compute overall probability of getting loan\n",
+        "pr_get_loan_p0 = compute_probability_get_loan(credit_scores, freq_y0_p0+freq_y1_p0, tau0)\n",
+        "pr_get_loan_p1 = compute_probability_get_loan(credit_scores, freq_y0_p1+freq_y1_p1, tau1)\n",
+        "print(\"Probability blue group gets loan = %3.3f\"%(pr_get_loan_p0))\n",
+        "print(\"Probability yellow group gets loan = %3.3f\"%(pr_get_loan_p1))"
+      ]
+    },
+    {
+      "attachments": {},
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "5QrtvZZlHCJy"
+      },
+      "source": [
+        "This is good, because now both groups get roughly the same amount of loans.  But hold on... let's look at the ROC curve:"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "VApyl_58GUQb"
+      },
+      "outputs": [],
+      "source": [
+        "plot_roc(credit_scores, freq_y0_p0, freq_y1_p0, freq_y0_p1, freq_y1_p1, tau0, tau1)"
+      ]
+    },
+    {
+      "attachments": {},
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "_GgX_b6yIE4W"
+      },
+      "source": [
+        "The blue dot is waaay above the yellow dot. The proportion of people who are given a load and do pay it back from the blue population is much higher than that from the yellow population.  From another perspective, that's unfair... it seems like the yellow population are 'allowed' to default more often than the blue. This leads to another possibility."
+      ]
+    },
+    {
+      "attachments": {},
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "WDnaqetXHhlv"
+      },
+      "source": [
+        "# Equal opportunity:\n",
+        "\n",
+        "The thresholds are chosen so that so that the true positive rate is is the same for both population. Of the people who pay back the loan, the same proportion are offered credit in each group. In terms of the two ROC curves, it means choosing thresholds so that the vertical position on each curve is the same without regard for the horizontal position."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "zEN6HGJ7HJAZ"
+      },
+      "outputs": [],
+      "source": [
+        "# TO DO -- try to change the two thresholds so the true positive are 0.8 for each group\n",
+        "# Change the values in these lines so that both points on the curves have a height of 0.8\n",
+        "tau0 = -0.1\n",
+        "tau1 = -0.7\n",
+        "\n",
+        "\n",
+        "plot_roc(credit_scores, freq_y0_p0, freq_y1_p0, freq_y0_p1, freq_y1_p1, tau0, tau1)"
+      ]
+    },
+    {
+      "attachments": {},
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "JsyW0pBGJ24b"
+      },
+      "source": [
+        "This seems fair -- people who are given loans default at the same rate (20%) for both groups.  But hold on... let's look at the overall loan rate between the two populations:"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "2a5PXHeNJDjg"
+      },
+      "outputs": [],
+      "source": [
+        "# Compute overall probability of getting loan\n",
+        "pr_get_loan_p0 = compute_probability_get_loan(credit_scores, freq_y0_p0+freq_y1_p0, tau0)\n",
+        "pr_get_loan_p1 = compute_probability_get_loan(credit_scores, freq_y0_p1+freq_y1_p1, tau1)\n",
+        "print(\"Probability blue group gets loan = %3.3f\"%(pr_get_loan_p0))\n",
+        "print(\"Probability yellow group gets loan = %3.3f\"%(pr_get_loan_p1))"
+      ]
+    },
+    {
+      "attachments": {},
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "tZTM7N6jKC7q"
+      },
+      "source": [
+        "The conclusion from all this is that (i) definitions of fairness are quite subtle and (ii) it's not possible to satisfy them all simultaneously."
+      ]
+    }
+  ],
+  "metadata": {
+    "colab": {
+      "authorship_tag": "ABX9TyNQPfTDV6PFG7Ctcl+XVNlz",
+      "include_colab_link": true,
+      "provenance": []
+    },
+    "kernelspec": {
+      "display_name": "Python 3",
+      "name": "python3"
+    },
+    "language_info": {
+      "name": "python"
+    }
+  },
+  "nbformat": 4,
+  "nbformat_minor": 0
+}

Notebooks/Chap21/21_2_Explainability.ipynb

@@ -0,0 +1,412 @@
+{
+  "nbformat": 4,
+  "nbformat_minor": 0,
+  "metadata": {
+    "colab": {
+      "provenance": [],
+      "authorship_tag": "ABX9TyOLMPuSWpvv8BfyPV36RuJP",
+      "include_colab_link": true
+    },
+    "kernelspec": {
+      "name": "python3",
+      "display_name": "Python 3"
+    },
+    "language_info": {
+      "name": "python"
+    }
+  },
+  "cells": [
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "view-in-github",
+        "colab_type": "text"
+      },
+      "source": [
+        "<a href=\"https://colab.research.google.com/github/udlbook/udlbook/blob/main/Notebooks/Chap21/21_2_Explainability.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "# **Notebook 21.2: Explainability**\n",
+        "\n",
+        "This notebook investigates the LIME explainability method as depicted in figure 21.3 of the book.\n",
+        "\n",
+        "Work through the cells below, running each cell in turn. In various places you will see the words \"TO DO\". Follow the instructions at these places and make predictions about what is going to happen or write code to complete the functions.\n",
+        "\n",
+        "Contact me at udlbookmail@gmail.com if you find any mistakes or have any suggestions.\n"
+      ],
+      "metadata": {
+        "id": "t9vk9Elugvmi"
+      }
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "import numpy as np\n",
+        "import matplotlib.pyplot as plt\n",
+        "import numpy.matlib\n",
+        "from matplotlib.colors import ListedColormap"
+      ],
+      "metadata": {
+        "id": "yC_LpiJqZXEL"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "First we'll build a black box model for predicting a credit score.  This simulates a neural network.  It takes four inputs $x1,x2,x3,x4$ in a column vector and it returns a value $y$.  Let's assume that if the output $y$ is greater than 0 then you get the loan, and if the output is less than 0 then you don't get the zone."
+      ],
+      "metadata": {
+        "id": "WM6mq9KNit3j"
+      }
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "# Details of this not important -- a hacky thing that takes four inputs and returns\n",
+        "# a scalar output\n",
+        "class BlackBoxModel:\n",
+        "  def __init__(self):\n",
+        "    self.n_dim = 4\n",
+        "    self.n_points = 10\n",
+        "    self.means = np.random.uniform(size=(self.n_dim, self.n_points))\n",
+        "    self.stds = np.random.uniform(size=(self.n_dim,self.n_points))+0.1\n",
+        "    self.values = np.random.normal(size=(self.n_points))/10\n",
+        "    self.values = self.values - np.mean(self.values)\n",
+        "\n",
+        "\n",
+        "  def intensity(self, x, mean, std, value):\n",
+        "\n",
+        "    dist = (x-np.matlib.repmat(mean,1,x.shape[1])) / np.matlib.repmat(std,1,x.shape[1])\n",
+        "    out = value * np.exp(-np.sum(dist*dist,axis=0))\n",
+        "    out = out[None,:]\n",
+        "    return out\n",
+        "\n",
+        "\n",
+        "  def get_output(self,x):\n",
+        "    y = np.zeros((1,x.shape[1]))\n",
+        "    t_vals = np.arange(0, self.n_points-1, 0.01)\n",
+        "    for t in t_vals:\n",
+        "      i = np.floor(t)\n",
+        "      prop = t-i\n",
+        "      i = int(i)\n",
+        "      y = y+ prop  * self.intensity(x, self.means[:,[i]], self.stds[:,[i]], self.values[i])\n",
+        "      y = y+ (1-prop) * self.intensity(x,self.means[:,[i+1]], self.stds[:,[i+1]], self.values[i+1])\n",
+        "      y = np.clip(y,-10,10)\n",
+        "    return y"
+      ],
+      "metadata": {
+        "id": "rt4FS42dIa9_"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "# Code to draw 2D slide through the four dimensional function\n",
+        "# Again, you don't really need to read this.\n",
+        "def draw_2D_slice(model, dim1, dim2, first_other_dim_value = 0.5, second_other_dim_value = 0.6):\n",
+        "\n",
+        "    #Create pretty colormap as in book\n",
+        "    my_colormap_vals_hex =('2a0902', '2b0a03', '2c0b04', '2d0c05', '2e0c06', '2f0d07', '300d08', '310e09', '320f0a', '330f0b', '34100b', '35110c', '36110d', '37120e', '38120f', '39130f', '3a1410', '3b1411', '3c1511', '3d1612', '3e1613', '3f1713', '401714', '411814', '421915', '431915', '451a16', '461b16', '471b17', '481c17', '491d18', '4a1d18', '4b1e19', '4c1f19', '4d1f1a', '4e201b', '50211b', '51211c', '52221c', '53231d', '54231d', '55241e', '56251e', '57261f', '58261f', '592720', '5b2821', '5c2821', '5d2922', '5e2a22', '5f2b23', '602b23', '612c24', '622d25', '632e25', '652e26', '662f26', '673027', '683027', '693128', '6a3229', '6b3329', '6c342a', '6d342a', '6f352b', '70362c', '71372c', '72372d', '73382e', '74392e', '753a2f', '763a2f', '773b30', '783c31', '7a3d31', '7b3e32', '7c3e33', '7d3f33', '7e4034', '7f4134', '804235', '814236', '824336', '834437', '854538', '864638', '874739', '88473a', '89483a', '8a493b', '8b4a3c', '8c4b3c', '8d4c3d', '8e4c3e', '8f4d3f', '904e3f', '924f40', '935041', '945141', '955242', '965343', '975343', '985444', '995545', '9a5646', '9b5746', '9c5847', '9d5948', '9e5a49', '9f5a49', 'a05b4a', 'a15c4b', 'a35d4b', 'a45e4c', 'a55f4d', 'a6604e', 'a7614e', 'a8624f', 'a96350', 'aa6451', 'ab6552', 'ac6552', 'ad6653', 'ae6754', 'af6855', 'b06955', 'b16a56', 'b26b57', 'b36c58', 'b46d59', 'b56e59', 'b66f5a', 'b7705b', 'b8715c', 'b9725d', 'ba735d', 'bb745e', 'bc755f', 'bd7660', 'be7761', 'bf7862', 'c07962', 'c17a63', 'c27b64', 'c27c65', 'c37d66', 'c47e67', 'c57f68', 'c68068', 'c78169', 'c8826a', 'c9836b', 'ca846c', 'cb856d', 'cc866e', 'cd876f', 'ce886f', 'ce8970', 'cf8a71', 'd08b72', 'd18c73', 'd28d74', 'd38e75', 'd48f76', 'd59077', 'd59178', 'd69279', 'd7937a', 'd8957b', 'd9967b', 'da977c', 'da987d', 'db997e', 'dc9a7f', 'dd9b80', 'de9c81', 'de9d82', 'df9e83', 'e09f84', 'e1a185', 'e2a286', 'e2a387', 'e3a488', 'e4a589', 'e5a68a', 'e5a78b', 'e6a88c', 'e7aa8d', 'e7ab8e', 'e8ac8f', 'e9ad90', 'eaae91', 'eaaf92', 'ebb093', 'ecb295', 'ecb396', 'edb497', 'eeb598', 'eeb699', 'efb79a', 'efb99b', 'f0ba9c', 'f1bb9d', 'f1bc9e', 'f2bd9f', 'f2bfa1', 'f3c0a2', 'f3c1a3', 'f4c2a4', 'f5c3a5', 'f5c5a6', 'f6c6a7', 'f6c7a8', 'f7c8aa', 'f7c9ab', 'f8cbac', 'f8ccad', 'f8cdae', 'f9ceb0', 'f9d0b1', 'fad1b2', 'fad2b3', 'fbd3b4', 'fbd5b6', 'fbd6b7', 'fcd7b8', 'fcd8b9', 'fcdaba', 'fddbbc', 'fddcbd', 'fddebe', 'fddfbf', 'fee0c1', 'fee1c2', 'fee3c3', 'fee4c5', 'ffe5c6', 'ffe7c7', 'ffe8c9', 'ffe9ca', 'ffebcb', 'ffeccd', 'ffedce', 'ffefcf', 'fff0d1', 'fff2d2', 'fff3d3', 'fff4d5', 'fff6d6', 'fff7d8', 'fff8d9', 'fffada', 'fffbdc', 'fffcdd', 'fffedf', 'ffffe0')\n",
+        "    my_colormap_vals_dec = np.array([int(element,base=16) for element in my_colormap_vals_hex])\n",
+        "    r = np.floor(my_colormap_vals_dec/(256*256))\n",
+        "    g = np.floor((my_colormap_vals_dec - r *256 *256)/256)\n",
+        "    b = np.floor(my_colormap_vals_dec - r * 256 *256 - g * 256)\n",
+        "    my_colormap_vals = np.vstack((r,g,b)).transpose()/255.0\n",
+        "    my_colormap = ListedColormap(my_colormap_vals)\n",
+        "\n",
+        "    x1_vals = np.arange(0.0, 1.0, 0.01)\n",
+        "    x2_vals = np.arange(0.0, 1.0, 0.01)\n",
+        "    x1_mesh, x2_mesh = np.meshgrid(x1_vals,x2_vals)\n",
+        "    n_vals = x1_mesh.shape[0]\n",
+        "\n",
+        "    x1 = np.reshape(x1_mesh,(1,n_vals*n_vals))\n",
+        "    x2 = np.reshape(x2_mesh,(1,n_vals*n_vals))\n",
+        "\n",
+        "    x = np.ones((4,n_vals*n_vals))\n",
+        "    x[dim1,:] = x1\n",
+        "    x[dim2,:] = x2\n",
+        "    if((dim1==0 and dim2 ==1) or (dim1==1 and dim2 ==0)):\n",
+        "      x[2,:] = x[2,:] * first_other_dim_value\n",
+        "      x[3,:] = x[3,:] * second_other_dim_value\n",
+        "      message = \"$x_{2}$ = %3.3f, $x_3$=%3.3f\"%(first_other_dim_value, second_other_dim_value)\n",
+        "    if((dim1==0 and dim2 ==2) or (dim1==2 and dim2 ==0)):\n",
+        "      x[1,:] = x[1,:] * first_other_dim_value\n",
+        "      x[3,:] = x[3,:] * second_other_dim_value\n",
+        "      message = \"$x_{1}$ = %3.3f, $x_3$=%3.3f\"%(first_other_dim_value, second_other_dim_value)\n",
+        "    if((dim1==0 and dim2 ==3) or (dim1==3 and dim2 ==0)):\n",
+        "      x[1,:] = x[1,:] * first_other_dim_value\n",
+        "      x[2,:] = x[2,:] * second_other_dim_value\n",
+        "      message = \"$x_{1}$ = %3.3f, $x_2$=%3.3f\"%(first_other_dim_value, second_other_dim_value)\n",
+        "    if((dim1==1 and dim2 ==2) or (dim1==2 and dim2 ==1)):\n",
+        "      x[0,:] = x[0,:] * first_other_dim_value\n",
+        "      x[3,:] = x[3,:] * second_other_dim_value\n",
+        "      message = \"$x_{0}$ = %3.3f, $x_3$=%3.3f\"%(first_other_dim_value, second_other_dim_value)\n",
+        "    if((dim1==1 and dim2 ==3) or (dim1==3 and dim2 ==1)):\n",
+        "      x[0,:] = x[0,:] * first_other_dim_value\n",
+        "      x[2,:] = x[2,:] * second_other_dim_value\n",
+        "      message = \"$x_{0}$ = %3.3f, $x_2$=%3.3f\"%(first_other_dim_value, second_other_dim_value)\n",
+        "    if((dim1==2 and dim2 ==3) or (dim1==3 and dim2 ==2)):\n",
+        "      x[0,:] = x[0,:] * first_other_dim_value\n",
+        "      x[1,:] = x[1,:] * second_other_dim_value\n",
+        "      message = \"$x_{0}$ = %3.3f, $x_1$=%3.3f\"%(first_other_dim_value, second_other_dim_value)\n",
+        "\n",
+        "    y = model.get_output(x)\n",
+        "    y[0,0] = -10; y[0,1]=10 # Hack the first two values so we see whole range of colormap\n",
+        "    y_mesh = np.reshape(y,(n_vals, n_vals))\n",
+        "\n",
+        "\n",
+        "    fig, ax = plt.subplots()\n",
+        "    fig.set_size_inches(7,7)\n",
+        "    pos = ax.contourf(x1_mesh, x2_mesh, y_mesh, levels=256 ,cmap = my_colormap, vmin=-10,vmax=10.0)\n",
+        "    ax.set_xlabel('Dimension x%d'%dim1);ax.set_ylabel('Dimension x%d'%dim2)\n",
+        "    ax.set_title(message)\n",
+        "    levels = np.array([0])\n",
+        "    ax.contour(x1_mesh, x2_mesh, y_mesh, levels, cmap=my_colormap)\n",
+        "    cb = fig.colorbar(pos)\n",
+        "    cb.set_ticks((-10,-5,0,5,10))\n",
+        "    plt.show()"
+      ],
+      "metadata": {
+        "id": "g0sosSU4RdU3"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "Create an instance of our model"
+      ],
+      "metadata": {
+        "id": "RlHjBpcyjcw4"
+      }
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "np.random.seed(3)\n",
+        "model = BlackBoxModel()"
+      ],
+      "metadata": {
+        "id": "-JXgQD4oT3J1"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "The four inputs to the model might represent the four inputs measures of our debt, age, income etc, and the output represents the credit score.\n",
+        "\n",
+        "As a responsible model owner, we want to understand our model and make sure that it is doing something sensible.  \n",
+        "\n",
+        "Unfortunately, the model describes a four dimensional function, which makes it really hard to understand (and imagine, that there could easily be hundreds of input in a real model).\n",
+        "\n",
+        "One thing that we can do it look at the effect of two of the inputs at one time.  For example, we can look at how inputs 0 and 1 change when we fix dimension 2 to 0.2 and dimension 3 to 0.9.   The black line represents the decision boundary (where the model predicts a credit score of zero).  If we are on the wrong side of this boundary, then our loan is refused."
+      ],
+      "metadata": {
+        "id": "6LxuB6p3k-VM"
+      }
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "draw_2D_slice(model,0,1,0.2,0.9)"
+      ],
+      "metadata": {
+        "id": "NblKr3W0dBJJ"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "Similarly, we could look at how inputs 1 and 3 change the input when we set input 0 to 0.3 and input 2 to 0.2:"
+      ],
+      "metadata": {
+        "id": "Fp2GeFn5mIRW"
+      }
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "draw_2D_slice(model,1,3,0.3,0.2)"
+      ],
+      "metadata": {
+        "id": "VzIe0py5d5Bk"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "This tells us something -- it might be good for a reality check if we had some expectations about what effect each input would have, but it's still hard to ensure that the model does something sensible everywhere, especially for models where there are thousands of inputs.  Unfortunately, there are basically no good solutions to this problem at the time of writing."
+      ],
+      "metadata": {
+        "id": "A9XUV9B6m7v0"
+      }
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "However, let's view this from the perspective of a customer.  We can assume that the four inputs have some particular values, and see what the output is."
+      ],
+      "metadata": {
+        "id": "1w968kJQjjUm"
+      }
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "x = np.array([[0.3],[0.8],[0.6],[0.3]])\n",
+        "y = model.get_output(x)\n",
+        "print(\"Your credit score is %3.3f\"%(y))\n",
+        "print(\"Sorry,  your loan is refused\")"
+      ],
+      "metadata": {
+        "id": "Nr71IahkjfV3"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "Well, that is bad news.  Why was our loan refused?  We'd like to understand what we could do to improve our credit score.   One way to do this is through individual conditional expectation or ICE plots ([Goldstein et al. 2015](https://arxiv.org/abs/1309.6392)). These take shows how the model output would change as we vary a single feature. Essentially, they answer the question: what if the $k^{th}$ feature had taken another value?"
+      ],
+      "metadata": {
+        "id": "mafmi3dSkTuf"
+      }
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "def ice_plot(model, x, k):\n",
+        "  # Get output for the input\n",
+        "  y = model.get_output(x)\n",
+        "\n",
+        "  # Possible values of the k'th dimension of the input\n",
+        "  x_k_all = np.arange(0,1,0.001)\n",
+        "  # TODO write code that varies the k'th dimension of x and runs the model on the result to create a series of outputs y\n",
+        "  # Replace this line\n",
+        "  y_all = np.zeros_like(x_k_all)\n",
+        "\n",
+        "\n",
+        "\n",
+        "  fig, ax = plt.subplots()\n",
+        "  ax.plot(x_k_all, np.squeeze(y_all), 'r-')\n",
+        "  ax.plot(x[k],y,'ro') ;\n",
+        "  ax.plot([0,1.0],[0.0,0.0],'k--')\n",
+        "  ax.set_xlabel('Dimension x%d'%(k))\n",
+        "  ax.set_ylabel('Credit score')\n",
+        "  ax.set_xlim(0,1)\n",
+        "  ax.set_ylim([-10,10])\n",
+        "\n",
+        "  plt.show()\n",
+        "\n"
+      ],
+      "metadata": {
+        "id": "v2nNsvW-m2fb"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "ice_plot(model, x, 0)\n",
+        "ice_plot(model, x, 1)\n",
+        "ice_plot(model, x, 2)\n",
+        "ice_plot(model, x, 3)"
+      ],
+      "metadata": {
+        "id": "5I91gzfSnL9N"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "We can learn something from this.  For example, decreasing the value of $x_{3}$ would be the most effective way to increase our credit score.  However, this might be impossible if it is a variable we can't control like our age.  Perhaps decreasing $x_0$ and $x_{1}$ might improve it further.  Well... perhaps, but we don't know what is going on in our model;  it might also make things much worse.\n",
+        "\n",
+        "Local interpretable model-agnostic explanations or LIME ([Ribeiro et al. 2016](https://arxiv.org/abs/1602.04938)) approximate the main machine learning model locally around a given input using a simpler model that is easier to understand.  \n",
+        "\n",
+        "The principle is simple.  First, we sample some points $\\mathbf{x}_{i}$ close to  the input $\\mathbf{x}$ that we are interested in.  Then we find the outputs $\\mathbf{y}_i$ that correspond to those inputs.  Now we have a training set, and we can train any other kind of model that explains this small area of the input space. This can be a model that is much more interpretable and easier to understand such as a linear model or a tree."
+      ],
+      "metadata": {
+        "id": "RmjuAR7HojtR"
+      }
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "# TODO -- Choose 100 points where each element of x is perturbed by noise sampled from a uniform distribution\n",
+        "# that takes values between [-0.05 and 0.05].  Then run these points through the model.\n",
+        "# Replace these lines\n",
+        "x_lime_train = np.matlib.repmat(x, 1, 100)\n",
+        "y_lime_train = np.ones((1,100))\n",
+        "\n",
+        "# BEGIN_ANSWER\n",
+        "x_lime_train = x_lime_train + np.random.uniform(low=-0.05,high=0.05,size=x_lime_train.shape)\n",
+        "y_lime_train = model.get_output(x_lime_train)\n",
+        "# END_ANSWER"
+      ],
+      "metadata": {
+        "id": "-GprSftsnS0M"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "We'll train a linear model:\n",
+        "\n",
+        "\\begin{equation}\n",
+        "y = \\beta_0 + \\boldsymbol\\phi^{T}\\mathbf{x}\n",
+        "\\end{equation}"
+      ],
+      "metadata": {
+        "id": "yTFDYbqGqmcA"
+      }
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "# TODO -- train this model using a least squares loss\n",
+        "# to find values for the offset \\beta_0 and the four slopes in \\phi\n",
+        "# One way to do this is with sklearn.linear_model\n",
+        "# Replace this line\n",
+        "beta = 0; phi = np.zeros((1,4))\n",
+        "\n",
+        "print(phi)"
+      ],
+      "metadata": {
+        "id": "5e4VPh40qlEl"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "This model is easily interpretable.  The k'th coefficient tells us the how much (and in which direction) changing the value of the k'th input will change the output.  This is only valid in the vicinity of the input $x$.\n",
+        "\n",
+        "Note that a more sophisticated version of LIME would weight the training points according to how close they are to the original data point of interest."
+      ],
+      "metadata": {
+        "id": "hsZHWuVWtzIK"
+      }
+    }
+  ]
+}

index.html

@@ -11,15 +11,18 @@
     <div>
         <h1 style="margin: 0; font-size: 36px">Understanding Deep Learning</h1>
         by Simon J.D. Prince
-        <br>To be published by MIT Press Dec 5th 2023.<br>
+        <br>Published by MIT Press Dec 5th 2023.<br>
         <ul>
             <li>
-                <p style="font-size: larger; margin-bottom: 0">Download draft PDF Chapters 1-21 <a
+                <p style="font-size: larger; margin-bottom: 0">Download full PDF <a
-                        href="https://github.com/udlbook/udlbook/releases/download/v1.14/UnderstandingDeepLearning_13_10_23_C.pdf">here</a>
+                        href="https://github.com/udlbook/udlbook/releases/download/v.1.20/UnderstandingDeepLearning_16_1_24_C.pdf">here</a>
-                </p>2023-10-13. CC-BY-NC-ND license<br>
+                </p>2024-01-16. CC-BY-NC-ND license<br>
                 <img src="https://img.shields.io/github/downloads/udlbook/udlbook/total" alt="download stats shield">
             </li>
-            <li> Report errata via <a href="https://github.com/udlbook/udlbook/issues">github</a>
+            <li> Order your copy from  <a href="https://mitpress.mit.edu/9780262048644/understanding-deep-learning/">here </a></li>
+            <li> Known errata can be found here:   <a
+            href="https://github.com/udlbook/udlbook/raw/main/UDL_Errata.pdf">PDF</a></li>
+            <li> Report new errata via <a href="https://github.com/udlbook/udlbook/issues">github</a>
                 or contact me directly at udlbookmail@gmail.com
             <li> Follow me on <a href="https://twitter.com/SimonPrinceAI">Twitter</a> or <a
                     href="https://www.linkedin.com/in/simon-prince-615bb9165/">LinkedIn</a> for updates.
@@ -58,6 +61,7 @@
     <h2>Resources for instructors </h2>
     <p>Instructor answer booklet available with proof of credentials via <a
             href="https://mitpress.mit.edu/9780262048644/understanding-deep-learning"> MIT Press</a>.</p>
+    <p>Request an exam/desk copy via <a href="https://mitpress.ublish.com/request?cri=15055">MIT Press</a>.</p>
     <p>Figures in PDF (vector) / SVG (vector) / Powerpoint (images):
     <ul>
         <li> Chapter 1 - Introduction: <a href="https://github.com/udlbook/udlbook/raw/main/PDFFigures/UDLChap1PDF.zip">PDF
@@ -156,7 +160,7 @@
                 Figures</a>
         <li> Chapter 16 - Normalizing flows: <a
                 href="https://github.com/udlbook/udlbook/raw/main/PDFFigures/UDLChap16PDF.zip">PDF Figures</a> / <a
-                href="https://drive.google.com/uc?export=download&id=1B9bxtmdugwtg-b7Y4AdQKAIEVWxjx8l3"> SVG Figures</a>
+                href="https://drive.google.com/uc?export=download&id=1B9bxtmdugwtg-b7Y4AdQKAIEVWxjx8l3"> SVG Figures</a>                                                                                                     
             /
             <a href="https://docs.google.com/presentation/d/1nLLzqb9pdfF_h6i1HUDSyp7kSMIkSUUA/edit?usp=drive_link&ouid=110441678248547154185&rtpof=true&sd=true">PowerPoint
                 Figures</a>
@@ -168,7 +172,9 @@
                 Figures</a>
         <li> Chapter 18 - Diffusion models: <a
                 href="https://github.com/udlbook/udlbook/raw/main/PDFFigures/UDLChap18PDF.zip">PDF Figures</a> / <a
-                href="https://docs.google.com/presentation/d/1x_ufIBtVPzWUvRieKMkpw5SdRjXWwdfR/edit?usp=drive_link&ouid=110441678248547154185&rtpof=true&sd=true">
+                href="https://drive.google.com/uc?export=download&id=1A-pIGl4PxjVMYOKAUG3aT4a8wD3G-q_r"> SVG Figures</a>
+            /
+            <a href="https://docs.google.com/presentation/d/1x_ufIBtVPzWUvRieKMkpw5SdRjXWwdfR/edit?usp=drive_link&ouid=110441678248547154185&rtpof=true&sd=true">
             PowerPoint Figures</a>
         <li> Chapter 19 - Deep reinforcement learning: <a
                 href="https://github.com/udlbook/udlbook/raw/main/PDFFigures/UDLChap19PDF.zip">PDF Figures</a> / <a
@@ -199,6 +205,23 @@
     Instructions for editing figures / equations can be found <a
         href="https://drive.google.com/file/d/1T_MXXVR4AfyMnlEFI-UVDh--FXI5deAp/view?usp=sharing">here</a>.
 
+    <p> My slides for 20 lecture undergraduate deep learning course:</p>
+    <ul>
+        <li><a href="https://drive.google.com/uc?export=download&id=17RHb11BrydOvxSFNbRIomE1QKLVI087m">1. Introduction</a></li>
+        <li><a href="https://drive.google.com/uc?export=download&id=1491zkHULC7gDfqlV6cqUxyVYXZ-de-Ub">2. Supervised Learning</a></li>
+        <li><a href="https://drive.google.com/uc?export=download&id=1XkP1c9EhOBowla1rT1nnsDGMf2rZvrt7">3. Shallow Neural Networks</a></li>
+        <li><a href="https://drive.google.com/uc?export=download&id=1e2ejfZbbfMKLBv0v-tvBWBdI8gO3SSS1">4. Deep Neural Networks</a></li>
+        <li><a href="https://drive.google.com/uc?export=download&id=1fxQ_a1Q3eFPZ4kPqKbak6_emJK-JfnRH">5. Loss Functions</a></li>
+        <li><a href="https://drive.google.com/uc?export=download&id=17QQ5ZzXBtR_uCNCUU1gPRWWRUeZN9exW">6. Fitting Models</a></li>
+        <li><a href="https://drive.google.com/uc?export=download&id=1hC8JUCOaFWiw3KGn0rm7nW6mEq242QDK">7. Computing Gradients</a></li>
+        <li><a href="https://drive.google.com/uc?export=download&id=1tSjCeAVg0JCeBcPgDJDbi7Gg43Qkh9_d">7b. Initialization</a></li>
+        <li><a href="https://drive.google.com/uc?export=download&id=1RVZW3KjEs0vNSGx3B2fdizddlr6I0wLl">8. Performance</a></li>
+        <li><a href="https://drive.google.com/uc?export=download&id=1LTicIKPRPbZRkkg6qOr1DSuOB72axood">9. Regularization</a></li>
+        <li><a href="https://drive.google.com/uc?export=download&id=1bGVuwAwrofzZdfvj267elIzkYMIvYFj0">10. Convolutional Networks</a></li>
+        <li><a href="https://drive.google.com/uc?export=download&id=14w31QqWRDix1GdUE-na0_E0kGKBhtKzs">11. Image Generation</a></li>
+        <li><a href="https://drive.google.com/uc?export=download&id=1af6bTTjAbhDYfrDhboW7Fuv52Gk9ygKr">12. Transformers and LLMs</a></li>
+    </ul>
+
     <h2>Resources for students</h2>
 
     <p>Answers to selected questions: <a
@@ -342,29 +365,29 @@
         <li> Notebook 13.4 - Graph attention: <a
                 href="https://github.com/udlbook/udlbook/blob/main/Notebooks/Chap13/13_4_Graph_Attention_Networks.ipynb">ipynb/colab </a>
         </li>
-        <li> Notebook 15.1 - GAN toy example: (coming soon)</li>
+        <li> Notebook 15.1 - GAN toy example: <a href="https://github.com/udlbook/udlbook/blob/main/Notebooks/Chap15/15_1_GAN_Toy_Example.ipynb">ipynb/colab </a></li>
-        <li> Notebook 15.2 - Wasserstein distance: (coming soon)</li>
+        <li> Notebook 15.2 - Wasserstein distance: <a href="https://github.com/udlbook/udlbook/blob/main/Notebooks/Chap15/15_2_Wasserstein_Distance.ipynb">ipynb/colab </a></li>
-        <li> Notebook 16.1 - 1D normalizing flows: (coming soon)</li>
+        <li> Notebook 16.1 - 1D normalizing flows: <a href="https://github.com/udlbook/udlbook/blob/main/Notebooks/Chap16/16_1_1D_Normalizing_Flows.ipynb">ipynb/colab </a></li>
-        <li> Notebook 16.2 - Autoregressive flows: (coming soon)</li>
+        <li> Notebook 16.2 - Autoregressive flows: <a href="https://github.com/udlbook/udlbook/blob/main/Notebooks/Chap16/16_2_Autoregressive_Flows.ipynb">ipynb/colab </a></li>
-        <li> Notebook 16.3 - Contraction mappings: (coming soon)</li>
+        <li> Notebook 16.3 - Contraction mappings: <a href="https://github.com/udlbook/udlbook/blob/main/Notebooks/Chap16/16_3_Contraction_Mappings.ipynb">ipynb/colab </a></li>
-        <li> Notebook 17.1 - Latent variable models: (coming soon)</li>
+        <li> Notebook 17.1 - Latent variable models: <a href="https://github.com/udlbook/udlbook/blob/main/Notebooks/Chap17/17_1_Latent_Variable_Models.ipynb">ipynb/colab </a></li>
-        <li> Notebook 17.2 - Reparameterization trick: (coming soon)</li>
+        <li> Notebook 17.2 - Reparameterization trick: <a href="https://github.com/udlbook/udlbook/blob/main/Notebooks/Chap17/17_2_Reparameterization_Trick.ipynb">ipynb/colab </a></li>
-        <li> Notebook 17.3 - Importance sampling: (coming soon)</li>
+        <li> Notebook 17.3 - Importance sampling: <a href="https://github.com/udlbook/udlbook/blob/main/Notebooks/Chap17/17_3_Importance_Sampling.ipynb">ipynb/colab </a></li>
-        <li> Notebook 18.1 - Diffusion encoder: (coming soon)</li>
+        <li> Notebook 18.1 - Diffusion encoder: <a href="https://github.com/udlbook/udlbook/blob/main/Notebooks/Chap18/18_1_Diffusion_Encoder.ipynb">ipynb/colab </a></li>
-        <li> Notebook 18.2 - 1D diffusion model: (coming soon)</li>
+        <li> Notebook 18.2 - 1D diffusion model: <a href="https://github.com/udlbook/udlbook/blob/main/Notebooks/Chap18/18_2_1D_Diffusion_Model.ipynb">ipynb/colab </a></li>
-        <li> Notebook 18.3 - Reparameterized model: (coming soon)</li>
+        <li> Notebook 18.3 - Reparameterized model: <a href="https://github.com/udlbook/udlbook/blob/main/Notebooks/Chap18/18_3_Reparameterized_Model.ipynb">ipynb/colab </a></li>
-        <li> Notebook 18.4 - Families of diffusion models: (coming soon)</li>
+        <li> Notebook 18.4 - Families of diffusion models: <a href="https://github.com/udlbook/udlbook/blob/main/Notebooks/Chap18/18_4_Families_of_Diffusion_Models.ipynb">ipynb/colab </a></li>
-        <li> Notebook 19.1 - Markov decision processes: (coming soon)</li>
+        <li> Notebook 19.1 - Markov decision processes: <a href="https://github.com/udlbook/udlbook/blob/main/Notebooks/Chap19/19_1_Markov_Decision_Processes.ipynb">ipynb/colab </a></li>
-        <li> Notebook 19.2 - Dynamic programming: (coming soon)</li>
+        <li> Notebook 19.2 - Dynamic programming: <a href="https://github.com/udlbook/udlbook/blob/main/Notebooks/Chap19/19_2_Dynamic_Programming.ipynb">ipynb/colab </a></li>
-        <li> Notebook 19.3 - Monte-Carlo methods: (coming soon)</li>
+        <li> Notebook 19.3 - Monte-Carlo methods: <a href="https://github.com/udlbook/udlbook/blob/main/Notebooks/Chap19/19_3_Monte_Carlo_Methods.ipynb">ipynb/colab </a></li>
-        <li> Notebook 19.4 - Temporal difference methods: (coming soon)</li>
+        <li> Notebook 19.4 - Temporal difference methods: <a href="https://github.com/udlbook/udlbook/blob/main/Notebooks/Chap19/19_4_Temporal_Difference_Methods.ipynb">ipynb/colab </a></li>
-        <li> Notebook 19.5 - Control variates: (coming soon)</li>
+        <li> Notebook 19.5 - Control variates: <a href="https://github.com/udlbook/udlbook/blob/main/Notebooks/Chap19/19_5_Control_Variates.ipynb">ipynb/colab </a></li>
-        <li> Notebook 20.1 - Random data: (coming soon)</li>
+        <li> Notebook 20.1 - Random data: <a href="https://github.com/udlbook/udlbook/blob/main/Notebooks/Chap20/20_1_Random_Data.ipynb">ipynb/colab </a></li>
-        <li> Notebook 20.2 - Full-batch gradient descent: (coming soon)</li>
+        <li> Notebook 20.2 - Full-batch gradient descent: <a href="https://github.com/udlbook/udlbook/blob/main/Notebooks/Chap20/20_2_Full_Batch_Gradient_Descent.ipynb">ipynb/colab </a></li>
-        <li> Notebook 20.3 - Lottery tickets: (coming soon)</li>
+        <li> Notebook 20.3 - Lottery tickets: <a href="https://github.com/udlbook/udlbook/blob/main/Notebooks/Chap20/20_3_Lottery_Tickets.ipynb">ipynb/colab </a></li>
-        <li> Notebook 20.4 - Adversarial attacks: (coming soon)</li>
+        <li> Notebook 20.4 - Adversarial attacks: <a href="https://github.com/udlbook/udlbook/blob/main/Notebooks/Chap20/20_4_Adversarial_Attacks.ipynb">ipynb/colab </a></li>
-        <li> Notebook 21.1 - Bias mitigation: (coming soon)</li>
+        <li> Notebook 21.1 - Bias mitigation: <a href="https://github.com/udlbook/udlbook/blob/main/Notebooks/Chap21/21_1_Bias_Mitigation.ipynb">ipynb/colab </a></li>
-        <li> Notebook 21.2 - Explainability: (coming soon)</li>
+        <li> Notebook 21.2 - Explainability: <a href="https://github.com/udlbook/udlbook/blob/main/Notebooks/Chap21/21_2_Explainability.ipynb">ipynb/colab </a></li>
     </ul>
 
 
@@ -380,4 +403,4 @@
 }
     </code></pre>
 </div>
-</body>
+</body>