dr_domi/udlbook
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Fix typos in Chap09 notebooks

Browse Source
This commit is contained in:
Youcef Rahal
2024-05-06 20:20:35 -04:00
parent 14b751ff47
commit 89e8ebcbc5
1 changed files with 6 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files

12
Notebooks/Chap09/9_1_L2_Regularization.ipynb
View File

@@ -178,7 +178,7 @@
"\n", "\n",
"def draw_loss_function(compute_loss, data, model, my_colormap, phi_iters = None):\n", "def draw_loss_function(compute_loss, data, model, my_colormap, phi_iters = None):\n",
"\n", "\n",
" # Make grid of intercept/slope values to plot\n", " # Make grid of offset/frequency values to plot\n",
" offsets_mesh, freqs_mesh = np.meshgrid(np.arange(-10,10.0,0.1), np.arange(2.5,22.5,0.1))\n", " offsets_mesh, freqs_mesh = np.meshgrid(np.arange(-10,10.0,0.1), np.arange(2.5,22.5,0.1))\n",
" loss_mesh = np.zeros_like(freqs_mesh)\n", " loss_mesh = np.zeros_like(freqs_mesh)\n",
" # Compute loss for every set of parameters\n", " # Compute loss for every set of parameters\n",
@@ -304,7 +304,7 @@
"for c_step in range (n_steps):\n", "for c_step in range (n_steps):\n",
" # Do gradient descent step\n", " # Do gradient descent step\n",
" phi_all[:,c_step+1:c_step+2] = gradient_descent_step(phi_all[:,c_step:c_step+1],data, model)\n", " phi_all[:,c_step+1:c_step+2] = gradient_descent_step(phi_all[:,c_step:c_step+1],data, model)\n",
" # Measure loss and draw model every 4th step\n", " # Measure loss and draw model every 8th step\n",
" if c_step % 8 == 0:\n", " if c_step % 8 == 0:\n",
" loss = compute_loss(data[0,:], data[1,:], model, phi_all[:,c_step+1:c_step+2])\n", " loss = compute_loss(data[0,:], data[1,:], model, phi_all[:,c_step+1:c_step+2])\n",
" draw_model(data,model,phi_all[:,c_step+1], \"Iteration %d, loss = %f\"%(c_step+1,loss))\n", " draw_model(data,model,phi_all[:,c_step+1], \"Iteration %d, loss = %f\"%(c_step+1,loss))\n",
@@ -369,7 +369,7 @@
"# Code to draw the regularization function\n", "# Code to draw the regularization function\n",
"def draw_reg_function():\n", "def draw_reg_function():\n",
"\n", "\n",
" # Make grid of intercept/slope values to plot\n", " # Make grid of offset/frequency values to plot\n",
" offsets_mesh, freqs_mesh = np.meshgrid(np.arange(-10,10.0,0.1), np.arange(2.5,22.5,0.1))\n", " offsets_mesh, freqs_mesh = np.meshgrid(np.arange(-10,10.0,0.1), np.arange(2.5,22.5,0.1))\n",
" loss_mesh = np.zeros_like(freqs_mesh)\n", " loss_mesh = np.zeros_like(freqs_mesh)\n",
" # Compute loss for every set of parameters\n", " # Compute loss for every set of parameters\n",
@@ -399,7 +399,7 @@
"# Code to draw loss function with regularization\n", "# Code to draw loss function with regularization\n",
"def draw_loss_function_reg(data, model, lambda_, my_colormap, phi_iters = None):\n", "def draw_loss_function_reg(data, model, lambda_, my_colormap, phi_iters = None):\n",
"\n", "\n",
" # Make grid of intercept/slope values to plot\n", " # Make grid of offset/frequency values to plot\n",
" offsets_mesh, freqs_mesh = np.meshgrid(np.arange(-10,10.0,0.1), np.arange(2.5,22.5,0.1))\n", " offsets_mesh, freqs_mesh = np.meshgrid(np.arange(-10,10.0,0.1), np.arange(2.5,22.5,0.1))\n",
" loss_mesh = np.zeros_like(freqs_mesh)\n", " loss_mesh = np.zeros_like(freqs_mesh)\n",
" # Compute loss for every set of parameters\n", " # Compute loss for every set of parameters\n",
@@ -512,7 +512,7 @@
"for c_step in range (n_steps):\n", "for c_step in range (n_steps):\n",
" # Do gradient descent step\n", " # Do gradient descent step\n",
" phi_all[:,c_step+1:c_step+2] = gradient_descent_step2(phi_all[:,c_step:c_step+1],lambda_, data, model)\n", " phi_all[:,c_step+1:c_step+2] = gradient_descent_step2(phi_all[:,c_step:c_step+1],lambda_, data, model)\n",
" # Measure loss and draw model every 4th step\n", " # Measure loss and draw model every 8th step\n",
" if c_step % 8 == 0:\n", " if c_step % 8 == 0:\n",
" loss = compute_loss2(data[0,:], data[1,:], model, phi_all[:,c_step+1:c_step+2], lambda_)\n", " loss = compute_loss2(data[0,:], data[1,:], model, phi_all[:,c_step+1:c_step+2], lambda_)\n",
" draw_model(data,model,phi_all[:,c_step+1], \"Iteration %d, loss = %f\"%(c_step+1,loss))\n", " draw_model(data,model,phi_all[:,c_step+1], \"Iteration %d, loss = %f\"%(c_step+1,loss))\n",
@@ -528,7 +528,7 @@
{ {
"cell_type": "markdown", "cell_type": "markdown",
"source": [ "source": [
"You should see that the gradient descent algorithm now finds the correct minimum. By applying a tiny bit of domain knowledge (the parameter phi0 tends to be near zero and the parameters phi1 tends to be near 12.5), we get a better solution. However, the cost is that this solution is slightly biased towards this prior knowledge." "You should see that the gradient descent algorithm now finds the correct minimum. By applying a tiny bit of domain knowledge (the parameter phi0 tends to be near zero and the parameter phi1 tends to be near 12.5), we get a better solution. However, the cost is that this solution is slightly biased towards this prior knowledge."
], ],
"metadata": { "metadata": {
"id": "wrszSLrqZG4k" "id": "wrszSLrqZG4k"