diff --git a/CM20315_Loss.ipynb b/CM20315_Loss.ipynb
index 9fe1ea8..2dada4c 100644
--- a/CM20315_Loss.ipynb
+++ b/CM20315_Loss.ipynb
@@ -4,7 +4,7 @@
   "metadata": {
     "colab": {
       "provenance": [],
-      "authorship_tag": "ABX9TyOqCPAhQYYC3FXImYjR63Vv",
+      "authorship_tag": "ABX9TyOCCH/LhDTTosau7DO302p4",
       "include_colab_link": true
     },
     "kernelspec": {
@@ -187,12 +187,12 @@
       "cell_type": "code",
       "source": [
         "# Return probability under normal distribution for input x\n",
-        "def normal_distribution(x, mu, sigma):\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",
         "    # Don't use the numpy version -- that's cheating!\n",
         "    # Replace the line below\n",
-        "    prob = np.zeros_like(x)\n",
+        "    prob = np.zeros_like(y)\n",
         "    return prob"
       ],
       "metadata": {
@@ -217,12 +217,12 @@
       "cell_type": "code",
       "source": [
         "# Let's plot the Gaussian distribution.\n",
-        "x_gauss = np.arange(-5,5,0.1)\n",
+        "y_gauss = np.arange(-5,5,0.1)\n",
         "mu = 0; sigma = 1.0\n",
-        "y_gauss = normal_distribution(x_gauss, mu, sigma)\n",
+        "gauss_prob = normal_distribution(y_gauss, mu, sigma)\n",
         "fig, ax = plt.subplots()\n",
-        "ax.plot(x_gauss, y_gauss)\n",
-        "ax.set_xlabel('Input, $x$'); ax.set_ylabel('Probability $Pr(x)$')\n",
+        "ax.plot(y_gauss, gauss_prob)\n",
+        "ax.set_xlabel('Input, $y$'); ax.set_ylabel('Probability $Pr(y)$')\n",
         "ax.set_xlim([-5,5]);ax.set_ylim([0,1.0])\n",
         "plt.show()\n",
         "\n",
@@ -236,10 +236,28 @@
         "# Answer:"
       ],
       "metadata": {
-        "id": "A2HcmNfUMIlj"
+        "colab": {
+          "base_uri": "https://localhost:8080/",
+          "height": 287
+        },
+        "id": "A2HcmNfUMIlj",
+        "outputId": "9c467e72-2973-4f5c-b42f-fb55ac62ad51"
       },
       "execution_count": null,
-      "outputs": []
+      "outputs": [
+        {
+          "output_type": "display_data",
+          "data": {
+            "text/plain": [
+              "<Figure size 432x288 with 1 Axes>"
+            ],
+            "image/png": "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\n"
+          },
+          "metadata": {
+            "needs_background": "light"
+          }
+        }
+      ]
     },
     {
       "cell_type": "markdown",