diff --git a/notebooks/Block_2/Exercises Block 2 - Neural Networks.ipynb b/notebooks/Block_2/Exercises Block 2 - Neural Networks.ipynb
index 848b5ae60deb427664171e5e2cdc2990a7b27df1..2aa140acdd7279cbe29979573f6928a4b961a63e 100644
--- a/notebooks/Block_2/Exercises Block 2 - Neural Networks.ipynb	
+++ b/notebooks/Block_2/Exercises Block 2 - Neural Networks.ipynb	
@@ -638,7 +638,7 @@
    "source": [
     "## TODO : set up a Keras model\n",
     "\n",
-    "If there are two labels, we use `binary_crossentropy` as loss function. In this case, we use"
+    "If there are two labels, we use `binary_crossentropy` as loss function. In this case, we use `sigmoid` as output layer."
    ]
   },
   {
@@ -703,7 +703,9 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "## TODO : read MNIST data and compute validation accuracy for a multinomial logistic regression model, see [Multinomial Logistic Regression](https://en.wikipedia.org/wiki/Multinomial_logistic_regression)"
+    "## TODO : read MNIST data and compute validation accuracy for a multinomial logistic regression model, see [Multinomial Logistic Regression](https://en.wikipedia.org/wiki/Multinomial_logistic_regression)\n",
+    "\n",
+    "If there are several labels, then we use `categorical_crossentropy` as loss function and the output layer should be a `softmax` layer."
    ]
   },
   {
diff --git a/notebooks/Block_2/Solutions to Exercises - Block 2.ipynb b/notebooks/Block_2/Solutions to Exercises - Block 2.ipynb
index e858721b511be9b97159c405339394230626ecc6..4ed6fdcce4c3f3c14ebd9ec400134b0b37005d1c 100644
--- a/notebooks/Block_2/Solutions to Exercises - Block 2.ipynb	
+++ b/notebooks/Block_2/Solutions to Exercises - Block 2.ipynb	
@@ -45,7 +45,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": 76,
    "metadata": {
     "colab": {},
     "colab_type": "code",
@@ -69,7 +69,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": 77,
    "metadata": {
     "colab": {},
     "colab_type": "code",
@@ -96,7 +96,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": 78,
    "metadata": {
     "colab": {},
     "colab_type": "code",
@@ -164,7 +164,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": 79,
    "metadata": {
     "colab": {},
     "colab_type": "code",
@@ -191,7 +191,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": 80,
    "metadata": {
     "colab": {},
     "colab_type": "code",
@@ -222,7 +222,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
+   "execution_count": 81,
    "metadata": {
     "colab": {},
     "colab_type": "code",
@@ -270,7 +270,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
+   "execution_count": 82,
    "metadata": {
     "colab": {},
     "colab_type": "code",
@@ -307,7 +307,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 8,
+   "execution_count": 83,
    "metadata": {
     "colab": {},
     "colab_type": "code",
@@ -317,16 +317,16 @@
     {
      "data": {
       "text/plain": [
-       "[<matplotlib.lines.Line2D at 0x7fd953358790>]"
+       "[<matplotlib.lines.Line2D at 0x7ff9ec12a190>]"
       ]
      },
-     "execution_count": 8,
+     "execution_count": 83,
      "metadata": {},
      "output_type": "execute_result"
     },
     {
      "data": {
-      "image/png": "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\n",
+      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAYsAAAEGCAYAAACUzrmNAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjMuMSwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy/d3fzzAAAACXBIWXMAAAsTAAALEwEAmpwYAAAkLElEQVR4nO3deZhc1Xnn8e9b1VVdvS/qbkloQRKIReygYOElMWBsjB3Dk9gxxElIhmfIxHiMJ84kJpkZx06cx86TQExiOyYxMV5i7Dj2mMdDbGQ2L8EGiV2SQUIIq4XQ1vveXfXOH/dUd6nVS0nq6qru+n2ep55777m3qt4rmn77nHPPOebuiIiIzCRW7ABERKT0KVmIiMislCxERGRWShYiIjIrJQsREZlVRbEDKISWlhZfs2ZNscMQEVlQtm7detjdW6c6tyiTxZo1a9iyZUuxwxARWVDM7JXpzqkZSkREZqVkISIis1KyEBGRWSlZiIjIrJQsRERkVkoWIiIyKyULERGZlZJFjle7Brn9gRd4+XB/sUMRESkpShY5jvSNcOdDu9h1sK/YoYiIlBQlixw1lXEA+ofHihyJiEhpUbLIUVsZzX7Sp2QhInIUJYscNSFZDIwoWYiI5FKyyFGViGMGfcPpYociIlJSlCxyxGJGdSKuPgsRkUkKnizMLG5mT5nZd8PxWjP7mZntMrOvm1kylFeG413h/Jqcz7gtlL9gZm8rZLw1lRVKFiIik8xHzeJWYEfO8aeAO9z9dKATuCmU3wR0hvI7wnWY2QbgeuAc4Grgs2YWL1SwtZUV6uAWEZmkoMnCzFYC7wD+ORwbcAXwzXDJPcB1Yf/acEw4f2W4/lrgXncfdveXgV3ApYWKuaaygoER9VmIiOQqdM3i74A/BjLheAnQ5e7ZP93bgRVhfwWwFyCc7w7Xj5dP8Z45V52Mq2YhIjJJwZKFmb0TOOjuWwv1HZO+72Yz22JmWw4dOnTCn1OrPgsRkWMUsmbxBuBdZrYHuJeo+enTQKOZZdf+XgnsC/v7gFUA4XwDcCS3fIr3jHP3u9x9o7tvbG2dcr3xvKiDW0TkWAVLFu5+m7uvdPc1RB3UD7n7+4CHgXeHy24EvhP27wvHhPMPubuH8uvD01JrgfXA44WKu6aygn71WYiIHKVi9kvm3J8A95rZXwJPAV8I5V8Avmxmu4AOogSDu28zs28A24Ex4BZ3L9hv85qkxlmIiEw2L8nC3R8BHgn7u5niaSZ3HwLeM837PwF8onARTsg+DZXJOLGYzcdXioiUPI3gniQ7mWC/5ocSERmnZDHJxGSC6rcQEclSspgku6aFxlqIiExQspikJhmaoZQsRETGKVlMUqMFkEREjqFkMUm2g3tAa1qIiIxTspikOrsOt56GEhEZp2QxidbhFhE5lpLFJNk+C3Vwi4hMULKYpDqRfXRWfRYiIllKFpPEYkZNMs6AahYiIuOULKZQXVmhDm4RkRxKFlOI1uFWM5SISJaSxRRqKjVNuYhILiWLKdQktVqeiEguJYsp1KjPQkTkKEoWU4jW4VafhYhIlpLFFGor4xrBLSKSQ8liCjXJCo2zEBHJoWQxhWicRbQOt4iIKFlMqTbMPDswqn4LERFQspiSJhMUETmaksUUstOU9w4pWYiIgJLFlOpS2WQxWuRIRERKg5LFFOpSCUALIImIZClZTGGiZqFkISICShZTytYs1AwlIhJRspiCahYiIkdTsphCbTJKFj1KFiIigJLFlGIxo7ayQs1QIiKBksU06lIVaoYSEQmULKZRl6qgT8lCRARQsphWXSpB77CaoUREQMliWmqGEhGZoGQxjaiDW8lCRASULKZVl0roaSgRkUDJYhr1qQqNsxARCZQsplGXqmBkLMPwmBZAEhFRspjG+Myzql2IiBQuWZhZysweN7NnzGybmX0slK81s5+Z2S4z+7qZJUN5ZTjeFc6vyfms20L5C2b2tkLFnEvzQ4mITChkzWIYuMLdLwAuBK42s03Ap4A73P10oBO4KVx/E9AZyu8I12FmG4DrgXOAq4HPmlm8gHEDWi1PRCRXwZKFR/rCYSK8HLgC+GYovwe4LuxfG44J5680Mwvl97r7sLu/DOwCLi1U3FmaplxEZEJB+yzMLG5mTwMHgc3AS0CXu2f/XG8HVoT9FcBegHC+G1iSWz7Fe3K/62Yz22JmWw4dOnTSsWebofRElIhIgZOFu6fd/UJgJVFt4KwCftdd7r7R3Te2trae9OfVq2YhIjJuXp6Gcvcu4GHgMqDRzCrCqZXAvrC/D1gFEM43AEdyy6d4T8Gog1tEZEIhn4ZqNbPGsF8FXAXsIEoa7w6X3Qh8J+zfF44J5x9ydw/l14enpdYC64HHCxV3Vm1IFn3DShYiIhWzX3LClgP3hCeXYsA33P27ZrYduNfM/hJ4CvhCuP4LwJfNbBfQQfQEFO6+zcy+AWwHxoBb3L3gI+US8RipREzNUCIi5JEswhNJ7wPWufvHzWw1sMzdZ/zr3t2fBS6aonw3UzzN5O5DwHum+axPAJ+YLda5Fs0PpZqFiEg+zVCfJepruCEc9wKfKVhEJUTTlIuIRPJphnqdu19sZk8BuHtndtT1YleXStCjZigRkbxqFqOh38Eh6rgGMgWNqkTUq2YhIgLklyzuBL4NtJnZJ4AfA39V0KhKRLQAkmoWIiKzNkO5+1fNbCtwJWDAde6+o+CRlYC6VIUenRURYYZkYWbNOYcHga/lnnP3jkIGVgrqUgl6BpUsRERmqllsJeqnMGA10QyxBjQCvwDWFjq4YmuoSjA4mmZkLEOyQkt/iEj5mvY3oLuvdfd1wA+AX3X3FndfArwTeGC+AiymhqpofqjuQfVbiEh5y+fP5U3ufn/2wN3/A3h94UIqHY3VShYiIpDfOItXzex/AV8Jx+8DXi1cSKWjXjULEREgv5rFDUAr0eOz3wbamBjNvahlm6F6lCxEpMzl8+hsB3DrPMRSctRnISISyWciwYcJo7dzufsVBYmohGSTRdfASJEjEREprnz6LP4oZz8F/DrRVOGL3kTNoixuV0RkWvk0Q22dVPQTMyv44kOlIBGPUZOMqxlKRMpePs1QuSO5Y8AlREueloWGqoSShYiUvXyaoXJHco8BLwM3FTKoUlKvZCEikleyODusYjfOzCoLFE/JaaxO0D2oDm4RKW/5jLP4zynKHpvrQEqVmqFERGaedXYZsAKoMrOLiJqhAOqB6nmIrSQoWYiIzNwM9Tbgd4GVwO055b3AnxYwppKiZCEiMkOycPd7gHvM7Nfd/d/nMaaS0lidZGg0w9BomlQiXuxwRESKYqZmqN9y968Aa8zsDyefd/fbp3jbolOfMz+UkoWIlKuZmqFqwrZ2PgIpVbnzQ7XVp4ocjYhIcczUDPX5sP3Y/IVTeprCmhadA+q3EJHylc8I7lbgvwJrcq939/9SuLBKR1N1EoCOfo21EJHylc+gvO8APyJaXjVd2HBKT3NNlCw086yIlLN8kkW1u/9JwSMpUeM1CyULESlj+Yzg/q6ZXVPwSEpUVTJOKhGjU81QIlLG8kkWtxIljEEz6zGzXjPrKXRgpaS5OklHvzq4RaR85bOeRd18BFLKmmqS6rMQkbKWz9NQF09R3A284u5lsYRcU3VSfRYiUtby6eD+LHAx8Fw4Pg94Hmgwsz9w9wcKFVypaKpJ0t45UOwwRESKJp8+i1eBi9z9Ene/BLgQ2A1cBfx1AWMrGc3VCQ3KE5Gylk+yOMPdt2UP3H07cJa77y5cWKWlqSZJ9+AoY+lMsUMRESmKfJqhtpnZ54B7w/F7ge1htbyy+HM7O9aia3CUltqyWSRQRGRcPjWL3wV2AR8Kr92hbBS4vDBhlZamMIpbYy1EpFzl8+jsIPC34TVZ35xHVIKaQ81C/RYiUq5mrVmY2Xoz+6aZbTez3dlXHu9bZWYPh/dtM7NbQ3mzmW02s51h2xTKzczuNLNdZvZs7iO7ZnZjuH6nmd14Mjd8IhrDzLOaTFBEylU+zVD/AnwOGCNqdvoS8JU83jcGfNjdNwCbgFvMbAPwEeBBd18PPBiOAd4OrA+vm8N3YmbNwEeB1wGXAh/NJpj5kp1MUMlCRMpVPsmiyt0fBMzdX3H3PwfeMdub3H2/uz8Z9nuBHcAK4FrgnnDZPcB1Yf9a4Ese+SnQaGbLidYC3+zuHe7eCWwGrs73BufCktooWRzpG57PrxURKRn5PA01bGYxYKeZfQDYx3Gunmdma4CLgJ8BS919fzj1GrA07K8A9ua8rT2UTVc++TtuJqqRsHr16uMJb1aVFXHqUxUcVrIQkTKV70SC1cAHgUuA3wby7jcws1rg34EPuftRExC6uwOed7QzcPe73H2ju29sbW2di488SktdJYf71AwlIuUpn6ehngi7fcDvHc+Hm1mCKFF81d2/FYoPmNlyd98fmpkOhvJ9wKqct68MZfuAN08qf+R44pgLLbWVHOpVzUJEytO0ycLM7pvpje7+rpnOm5kBXwB2uPvtOafuI6qZfDJsv5NT/gEzu5eoM7s7JJTvA3+V06n9VuC2mb67EFprK9mxv6xmZhcRGTdTzeIyor6CrxH1NdhxfvYbiJqsnjOzp0PZnxIliW+Y2U3AK8BvhHP3A9cQDQAcINRi3L3DzP4CyNZwPu7uHccZy0lrqU1ySH0WIlKmZkoWy4gmC7wB+E3g/wFfy50naibu/mOmTzBXTnG9A7dM81l3A3fn872F0lJbSe/QGEOjaVKJeDFDERGZd9N2cLt72t2/5+43Eo2T2AU8Ep6IKjstddGcUEc01kJEytCMHdxhssB3ENUu1gB3At8ufFilJzuB4OHeYVY0VhU5GhGR+TVTB/eXgHOJ+hI+5u7Pz1tUJaglDMzTWAsRKUcz1Sx+C+gnGmfxwejhJiDqh3B3ry9wbCVlvGahZCEiZWjaZOHu+QzYKxutddlkoT4LESk/Sgh5SiXi1FVWaGCeiJQlJYvj0FqvUdwiUp6ULI7DsvoU+7sHix2GiMi8y2fxo5ow6yxmdoaZvSvM+VR2ltWnONCjmoWIlJ98ahY/BFJmtgJ4gGgKjy8WMqhStawhxYGeITKZOZkoV0RkwcgnWZi7DwC/BnzW3d8DnFPYsErTsoYUYxnncL9qFyJSXvJKFmZ2GfA+ovmhAMpycqRl9SkAXuseKnIkIiLzK59k8SGiKcG/7e7bzGwd8HBBoypRyxqULESkPOWz+NGjwKMAoaP7sLt/sNCBlaLxZNGjZCEi5SWfp6H+1czqzawGeB7Ybmb/s/ChlZ6WmkoqYqaahYiUnXyaoTaEtbOvA/4DWEv0RFTZicWMpfUpJQsRKTv5JItEGFdxHXCfu48CZfvs6NL6SvYrWYhImcknWXwe2APUAD80s1OBsl2MenlDlUZxi0jZmTVZuPud7r7C3a/xyCvA5fMQW0la1VzNvq5B0hqYJyJlJJ8O7gYzu93MtoTX3xLVMsrSquYqRtOuJ6JEpKzk0wx1N9AL/EZ49QD/UsigStnq5moA9nYMFDkSEZH5k0+yOM3dP+ruu8PrY8C6QgdWqrLJ4hdKFiJSRvJJFoNm9sbsgZm9ASjbHt5TGquImWoWIlJeZh3BDfw34Etm1hCOO4EbCxdSaUvEYyxvqFKyEJGyks90H88AF5hZfTjuMbMPAc8WOLaStbq5Ws1QIlJW8l4pz917wkhugD8sUDwLQpQsyrYlTkTK0Ikuq2pzGsUCs3pJNYf7hukfHit2KCIi8+JEk0VZj0hb1xINM3npUF+RIxERmR/T9lmYWS9TJwUDqgoW0QKwfmkdADsP9HH+ysbiBiMiMg+mTRbuXjefgSwka5ZUk4gbLx7sLXYoIiLz4kSbocpaRTzGupZadh1QM5SIlAclixO0fmmtahYiUjaULE7QGUvraO8cZGBET0SJyOKnZHGC1rfV4g4vHewvdigiIgWnZHGCNpxSD8Bz+7qLHImISOEpWZyg1c3VNNckeeoXncUORUSk4JQsTpCZceGqRp7e21XsUERECk7J4iRctKqRnQf76B4cLXYoIiIFVbBkYWZ3m9lBM3s+p6zZzDab2c6wbQrlZmZ3mtkuM3vWzC7Oec+N4fqdZlZSU6NftLoJgGfbu4obiIhIgRWyZvFF4OpJZR8BHnT39cCD4Rjg7cD68LoZ+BxEyQX4KPA64FLgo9kEUwrOX9WAGWzZo34LEVncCpYs3P2HQMek4muBe8L+PcB1OeVf8shPgUYzWw68Ddjs7h3u3gls5tgEVDT1qQQXrWrkkRcOFjsUEZGCmu8+i6Xuvj/svwYsDfsrgL0517WHsunKj2FmN5vZFjPbcujQobmNegZXnr2UZ9q7Odg7NG/fKSIy34rWwe3uzhxOde7ud7n7Rnff2NraOlcfO6srzmoD4JGfz1+CEhGZb/OdLA6E5iXCNtt+sw9YlXPdylA2XXnJOGtZHac0pPjetteKHYqISMHMd7K4D8g+0XQj8J2c8t8JT0VtArpDc9X3gbeaWVPo2H5rKCsZZsavXbySh184yF6tyy0ii1QhH539GvAYcKaZtZvZTcAngavMbCfwlnAMcD+wG9gF/BPwfgB37wD+AngivD4eykrKb206lZgZX3psT7FDEREpiGkXPzpZ7n7DNKeunOJaB26Z5nPuBu6ew9Dm3LKGFG8/dxn3Pr6X3/+V02iprSx2SCIic0ojuOfIh95yBoOjaf73/32eKPeJiCweShZz5PS2Wv7obWfyH8+/xof/7RmGRtPFDklEZM4UrBmqHP3+L69jZCzD7Ztf5IcvHubt5y7jzGV1rGiqYkVjFac0VlFbqX9yEVl49JtrDpkZH7xyPb+0ppl/+tFuvvVkO/0jR9cw6lMVnLeygavPWcavXnAKjdXJIkUrIpI/W4zt6xs3bvQtW7YUOwzSGedg7xCvdg2yrytsOwf5yUuH2X2on6pEnOsvXcVNb1zLyqbqYocrImXOzLa6+8apzqlmUUDxmLG8oYrlDVVccurR57a/2sM//3g3X37sFb782Cu8Z+MqPnDF6axorCpOsCIiM1DNosj2dQ3yj4+8xL1P/AKA639pNe+//DSWNyhpiMj8mqlmoWRRIvZ1DfKZh3fxjSf2EosZv3npat7/5tNoq08VOzQRKRNKFgvI3o4B/uGhXXzzyXbiZlx97jJuuHQ1m9Y1Y2bFDk9EFjEliwXolSP9/MtP9vCtJ9vpGRpjzZJq3nn+KVxz3nLOXl6nxCEic07JYgEbGk1z/3P7+ebWdn66+wgZhzVLqrnmvOW87ZxlnLeigVhMiUNETp6SxSJxpG+Y7287wP3P7eex3UdIZ5yl9ZVcefZSrtqwlNeftoTKinixwxSRBUrJYhHq7B/hoZ8f5Ac7DvDoi4cYGElTk4zzK2e2ctWGpVx+ZpsG/InIcVGyWOSGRtM89tIRHth+gB/sOMCh3mHiMePSNc28ZcNS3rphKauaNehPRGamZFFGMhnnmfYuNofE8eKBPiBa0e+qDVFz1XkrGtRBLiLHULIoY3sO9/ODHQd4YPsBtuzpIOOwtL6St4R+jk3rlpBKqJ9DRJQsJOjI9nNsP8APd0b9HKlEjNetXcKb1rfwy2e0sr6tVrUOkTKlZCHHyPZzPPriIX608xAvHeoHYFl9ijetb+FNZ7TyxtNbaK5RJ7lIudBEgnKMVCLO5We1cflZbUA03ciPdx7ihy8e5oHtB/i3re2YwbmnNPCm9S28cX0LF69uUpOVSJlSzUKOkc44z+3r5kcvHuJHOw/z5C86Gcs4yYoYF61qZNO6JVx22hIuXNWo5CGyiKgZSk5K79AoT+zp4LGXjvDT3R1se7WbjEOyIsbFqxu5bF0Lm9Y1c+HqRg0KFFnAlCxkTnUPjvLEyx38dPcRfvryEba92oM7VFbEuHBVI5ec2sTGNU1cvLpJAwNFFhAlCymo7oFRHg81j62vdLDt1R7GMtHP1elttWw8tYmLT21i46lNrG2p0dNWIiVKyULm1eBImmfau9j6Suf4q3twFIDmmiQXr27i4lMbuWBlI+etbKA+lShyxCICehpK5llVMs6mdUvYtG4JEI0q3324jy17JpLHD3YcGL9+XUsN569s4PyVjVywqoFzTmlQx7lIiVHNQoqia2CEZ9u7eba9i2fC9kDPMBCtXX7G0jouCAlkwyn1nLm0jqqkEohIIakZShaEAz1DPLO3i2fbu3mmPdpmm69iBmtbathwSgNnL69jw/J6Niyvp7WuUn0gInNEyUIWJHdnb8cg2/d3s31/Lzv297D91R72dQ2OX7OkJsmGU+o5e3k9Zy+v44yldZzWWqtmLJEToD4LWZDMjNVLqlm9pJqrz10+Xt49MMqO13rYsT96bd/fwxf/cw8jY5nwPljdXM36tjrWL61lfVst69vqOK2thuqkfuRFToT+z5EFp6E6cVQHOsBoOsPLh/vZeaCPnQd72Xmwj50Henn0xYOMpqPasxmsbKqKkkhbLWtbaljTUsPalhra1JwlMiMlC1kUEvEYZyyNmqFgohYyms7wypEBdh3sZeeBPl4MSeTHOw8zks6MX1edjHPqkhrWtdSwpqWaNUtqxpPJkpqkEomUPSULWdQS8Rint9VyelstV587UZ7OOK92DbLnSD8vH45eew73s31/D9/b9hrpzERfXl1lBae2VLOqqZqVTVWsao62K8OxmrakHOinXMpSPGasaq5mVXM1b1rfetS50XSG9s5B9hyeSCSvdAzwwoFeHvz5wfG+kawlNUlWhgSSTSgrmqo4paGKZQ0p6lMVqpnIgqdkITJJIh5jbejLuHzSuUzGOdw/zN6OQdo7B2jvnNhuf7WHzdsOHNW8BVET17L6FMsaotfyhhTLGqpYVp/dT9FcnSQWU0KR0qVkIXIcYjGjrS5FW12KS05tOuZ8JuMc7B2mvXOA13qGeK17iP3dQ+P7P9vdwYGeofG5s7KS8RitdZW01lXSUhttW2uTRx1ntzWV+t9W5p9+6kTmUCxm4zWI6aQzzpG+4aOSyP7uIQ70DHG4L0o0T+/t5Ej/CFMNg6pKxEPySNJSW8mS2iSN1Umaq5M0VidorgnHNVFZXapCtRY5aUoWIvMsHjPa6lO01ae4YIbrxtIZOgZGONw7wqG+YQ73DnOob5hDvcMcDts9R/p58hdddA2MHFNbyYoZNE1OJOG4vipBfaoibBPU5ezXV1VQlYirv0UAJQuRklURj403ec3G3ekdHqOrf5SOgRE6B0bo7B+hc2A0bLNlo+ztGODZ9i46B0aP6aw/JoaYHZNA6iqjbW1lgtrKONWVFdRUVlCTjFOdrKC2soLqyjg1yQpqwra6Mq6FsRa4BZMszOxq4NNAHPhnd/9kkUMSKRlmFv0yTyVYvaQ67/cNjabpHRqjZ2g02g6O0jM0Ss/gGL1DE/u55w/19tEzOEbf8Bj9I2NTNpVNJRG3iWSSjJJMdSJOVTJOKhEjlYhHr4o4VckYqYpwnIyTqojOV4VrqpIxKiuy+9H5ykScZDxGIm6qDRXAgkgWZhYHPgNcBbQDT5jZfe6+vbiRiSxs2V/QrXWVJ/R+d2dwNE3/cJr+kDwGRtL0DY8xMGXZGH3DaQZGxugfSTMwPEZv7yhDoxkGR9IMj6Wj/dH0UWNdjlcyHiNZEb0ScYv24zES8RiV4+Wx8fKjtpPOJeJGRTxGRcyoiBnxeIxEzIjHjIq4UREL58I1R5XHbbwsEY9F21iMeNwmPiNcF48ZMctuKbmEtyCSBXApsMvddwOY2b3AtYCShUgRmUW1hepkxQknnOmMpqOkMTSaZnh0Yn/oqP2JsuGxNCNjmeiV9rBNMzrmjKSz5ZmJa8Yy9A2P5bxnYjua3aaLN9GqGcTNiMWMeE4SiccmJxbLKYMrzmrjz96xYc7jWSjJYgWwN+e4HXhd7gVmdjNwM8Dq1avnLzIRKYhEqAkUcyXFTMYZyzjpjDOayZBOh23GGUtnz0VJJZ1xRtPh3Pj5TM51uceZic9NO2PpDGl3MhknnYGMOxmPzk8uP7osZ9+jeJc1VBXk32KhJItZuftdwF0QTVFe5HBEZBGIxYxkeOy4ivLuoI8VO4A87QNW5RyvDGUiIjIPFkqyeAJYb2ZrzSwJXA/cV+SYRETKxoJohnL3MTP7APB9okdn73b3bUUOS0SkbCyIZAHg7vcD9xc7DhGRcrRQmqFERKSIlCxERGRWShYiIjIrJQsREZmVeb6zgC0gZnYIeOUkPqIFODxH4SwUuufyoHsuDyd6z6e6e+tUJxZlsjhZZrbF3TcWO475pHsuD7rn8lCIe1YzlIiIzErJQkREZqVkMbW7ih1AEeiey4PuuTzM+T2rz0JERGalmoWIiMxKyUJERGalZJHDzK42sxfMbJeZfaTY8cwVM7vbzA6a2fM5Zc1mttnMdoZtUyg3M7sz/Bs8a2YXFy/yE2dmq8zsYTPbbmbbzOzWUL5o79vMUmb2uJk9E+75Y6F8rZn9LNzb18M0/5hZZTjeFc6vKeoNnAQzi5vZU2b23XC8qO/ZzPaY2XNm9rSZbQllBf3ZVrIIzCwOfAZ4O7ABuMHM5n4h2+L4InD1pLKPAA+6+3rgwXAM0f2vD6+bgc/NU4xzbQz4sLtvADYBt4T/nov5voeBK9z9AuBC4Goz2wR8CrjD3U8HOoGbwvU3AZ2h/I5w3UJ1K7Aj57gc7vlyd78wZzxFYX+23V2vqJP/MuD7Oce3AbcVO645vL81wPM5xy8Ay8P+cuCFsP954IaprlvIL+A7wFXlct9ANfAk0Vr1h4GKUD7+c060PsxlYb8iXGfFjv0E7nVl+OV4BfBdwMrgnvcALZPKCvqzrZrFhBXA3pzj9lC2WC119/1h/zVgadhfdP8OoanhIuBnLPL7Ds0xTwMHgc3AS0CXu4+FS3Lva/yew/luYMm8Bjw3/g74YyATjpew+O/ZgQfMbKuZ3RzKCvqzvWAWP5LCcXc3s0X5DLWZ1QL/DnzI3XvMbPzcYrxvd08DF5pZI/Bt4KziRlRYZvZO4KC7bzWzNxc5nPn0RnffZ2ZtwGYz+3nuyUL8bKtmMWEfsCrneGUoW6wOmNlygLA9GMoXzb+DmSWIEsVX3f1boXjR3zeAu3cBDxM1wTSaWfYPw9z7Gr/ncL4BODK/kZ60NwDvMrM9wL1ETVGfZnHfM+6+L2wPEv1RcCkF/tlWspjwBLA+PEWRBK4H7ityTIV0H3Bj2L+RqE0/W/474QmKTUB3TtV2wbCoCvEFYIe7355zatHet5m1hhoFZlZF1EezgyhpvDtcNvmes/8W7wYe8tCovVC4+23uvtLd1xD9P/uQu7+PRXzPZlZjZnXZfeCtwPMU+me72B01pfQCrgFeJGrn/bNixzOH9/U1YD8wStReeRNRO+2DwE7gB0BzuNaIngp7CXgO2Fjs+E/wnt9I1K77LPB0eF2zmO8bOB94Ktzz88D/CeXrgMeBXcC/AZWhPBWOd4Xz64p9Dyd5/28GvrvY7znc2zPhtS37u6rQP9ua7kNERGalZigREZmVkoWIiMxKyUJERGalZCEiIrNSshARkVkpWciiZ2bpMDtn9jVnMwqb2RrLmc13huv+3MwGwojbbFnffMYgcjI03YeUg0F3v7DYQRBNWvdh4E+KHUguM6vwiXmURKakmoWUrbAmwF+HdQEeN7PTQ/kaM3sozP3/oJmtDuVLzezbFq0X8YyZvT58VNzM/smiNSQeCKOnp3I38F4za54Ux1E1AzP7IzP787D/iJndYWZbzGyHmf2SmX0rrFnwlzkfU2FmXw3XfNPMqsP7LzGzR8OEc9/PmQ7iETP7O4vWQrj15P81ZbFTspByUDWpGeq9Oee63f084B+IZi8F+HvgHnc/H/gqcGcovxN41KP1Ii4mGj0L0ToBn3H3c4Au4NeniaOPKGEc7y/nEY/WLPhHoikcbgHOBX7XzLIzpp4JfNbdzwZ6gPeHubH+Hni3u18SvvsTOZ+bdPeN7v63xxmPlCE1Q0k5mKkZ6ms52zvC/mXAr4X9LwN/HfavAH4Hxmd37bZoNbKX3f3pcM1WorVDpnMn8LSZ/c1xxJ+do+w5YJuHeX3MbDfRBHFdwF53/0m47ivAB4HvESWVzWG23TjRtC9ZXz+OGKTMKVlIufNp9o/HcM5+GpiuGQp37zKzfyWqHWSNcXQtPzXN52cmfVeGif+HJ8fuRHMCbXP3y6YJp3+6OEUmUzOUlLv35mwfC/v/STSDKcD7gB+F/QeBP4DxRYYaTvA7bwd+n4lf9AeANjNbYmaVwDtP4DNXm1k2Kfwm8GOiFdFas+VmljCzc04wZilzShZSDib3WXwy51yTmT1L1I/wP0LZfwd+L5T/NhN9DLcCl5vZc0TNTSe0Rru7HyZag6AyHI8CHyeaBXUz8PPp3z2tF4jWGd8BNAGfc/cRomm4P2VmzxDNvPv66T9CZHqadVbKVlgwZ2P45S0iM1DNQkREZqWahYiIzEo1CxERmZWShYiIzErJQkREZqVkISIis1KyEBGRWf1/HJk7XyckzeYAAAAASUVORK5CYII=\n",
       "text/plain": [
        "<Figure size 432x288 with 1 Axes>"
       ]
@@ -360,7 +360,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 9,
+   "execution_count": 84,
    "metadata": {
     "colab": {},
     "colab_type": "code",
@@ -371,7 +371,7 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "[[211.27141]]\n"
+      "[[211.31021]]\n"
      ]
     }
    ],
@@ -413,7 +413,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 10,
+   "execution_count": 85,
    "metadata": {
     "colab": {},
     "colab_type": "code",
@@ -424,7 +424,7 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "These are the layer variables: [array([[1.8298433]], dtype=float32), array([28.287079], dtype=float32)]\n"
+      "These are the layer variables: [array([[1.8242955]], dtype=float32), array([28.880667], dtype=float32)]\n"
      ]
     }
    ],
@@ -454,7 +454,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 8,
+   "execution_count": 86,
    "metadata": {
     "colab": {},
     "colab_type": "code",
@@ -466,19 +466,18 @@
      "output_type": "stream",
      "text": [
       "Finished training the model\n",
-      "[[211.74745]]\n",
-      "Model predicts that 100 degrees Celsius is: [[211.74745]] degrees Fahrenheit\n",
-      "These are the l0 variables: [array([[-0.47996262,  0.25047022, -0.1492717 ,  0.11854655]],\n",
-      "      dtype=float32), array([-3.2115366,  3.1785958, -2.868187 ,  2.7906501], dtype=float32)]\n",
-      "These are the l1 variables: [array([[ 1.1949005 ,  0.80858207,  0.48969162,  0.57684636],\n",
-      "       [-0.31273484, -1.1010896 , -0.36613086,  0.34995782],\n",
-      "       [-0.07984556,  0.8192047 , -0.63080776, -0.01728256],\n",
-      "       [-0.8315819 ,  0.24608922,  0.9040395 ,  0.02908712]],\n",
-      "      dtype=float32), array([-3.1562395 , -3.0874147 ,  2.3403091 , -0.54884386], dtype=float32)]\n",
-      "These are the l2 variables: [array([[-1.1158108 ],\n",
-      "       [-1.3494587 ],\n",
-      "       [ 0.6974325 ],\n",
-      "       [-0.21758062]], dtype=float32), array([3.0711133], dtype=float32)]\n"
+      "[[211.74742]]\n",
+      "Model predicts that 100 degrees Celsius is: [[211.74742]] degrees Fahrenheit\n",
+      "These are the l0 variables: [array([[0.5968949 , 0.02139384, 0.01172368, 0.35185102]], dtype=float32), array([ 3.484818 , -3.0073252, -2.7715163,  3.010582 ], dtype=float32)]\n",
+      "These are the l1 variables: [array([[ 0.20319672, -0.41102245,  0.7771168 , -0.7402758 ],\n",
+      "       [-0.7281887 ,  0.9473572 , -0.15004049,  0.12950596],\n",
+      "       [-0.96478873,  0.05949384, -0.2531712 ,  0.72464406],\n",
+      "       [-0.10805991, -0.88057184,  1.0134443 , -0.15393376]],\n",
+      "      dtype=float32), array([ 1.8714209, -3.126011 ,  3.3828623, -2.6109185], dtype=float32)]\n",
+      "These are the l2 variables: [array([[ 0.23399544],\n",
+      "       [-0.9353689 ],\n",
+      "       [ 1.1917399 ],\n",
+      "       [-0.6491724 ]], dtype=float32), array([3.2284596], dtype=float32)]\n"
      ]
     }
    ],
@@ -529,7 +528,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 67,
+   "execution_count": 87,
    "metadata": {},
    "outputs": [
     {
@@ -538,7 +537,7 @@
        "Text(0, 0.5, 'Broken O-rings')"
       ]
      },
-     "execution_count": 67,
+     "execution_count": 87,
      "metadata": {},
      "output_type": "execute_result"
     },
@@ -573,7 +572,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 68,
+   "execution_count": 88,
    "metadata": {},
    "outputs": [
     {
@@ -614,7 +613,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 69,
+   "execution_count": 89,
    "metadata": {},
    "outputs": [
     {
@@ -663,7 +662,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 70,
+   "execution_count": 90,
    "metadata": {},
    "outputs": [
     {
@@ -724,7 +723,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 71,
+   "execution_count": 91,
    "metadata": {},
    "outputs": [
     {
@@ -747,21 +746,21 @@
    "source": [
     "## TODO : set up a Keras model\n",
     "\n",
-    "If there are two labels, we use `binary_crossentropy` as loss function. In this case, we use `softmax` as output layer."
+    "If there are two labels, we use `binary_crossentropy` as loss function. In this case, we use `sigmoid` as output layer."
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 72,
+   "execution_count": 92,
    "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "<keras.callbacks.History at 0x7ff9ec4cf890>"
+       "<keras.callbacks.History at 0x7ff9e419c450>"
       ]
      },
-     "execution_count": 72,
+     "execution_count": 92,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -775,29 +774,22 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 73,
+   "execution_count": 93,
    "metadata": {},
    "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "WARNING:tensorflow:5 out of the last 9 calls to <function Model.make_predict_function.<locals>.predict_function at 0x7ff9ec4d09e0> triggered tf.function retracing. Tracing is expensive and the excessive number of tracings could be due to (1) creating @tf.function repeatedly in a loop, (2) passing tensors with different shapes, (3) passing Python objects instead of tensors. For (1), please define your @tf.function outside of the loop. For (2), @tf.function has experimental_relax_shapes=True option that relaxes argument shapes that can avoid unnecessary retracing. For (3), please refer to https://www.tensorflow.org/guide/function#controlling_retracing and https://www.tensorflow.org/api_docs/python/tf/function for  more details.\n"
-     ]
-    },
     {
      "data": {
       "text/plain": [
-       "[<matplotlib.lines.Line2D at 0x7ff9ec50e710>]"
+       "[<matplotlib.lines.Line2D at 0x7ff9ec0405d0>]"
       ]
      },
-     "execution_count": 73,
+     "execution_count": 93,
      "metadata": {},
      "output_type": "execute_result"
     },
     {
      "data": {
-      "image/png": "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\n",
+      "image/png": "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\n",
       "text/plain": [
        "<Figure size 432x288 with 1 Axes>"
       ]
@@ -819,14 +811,14 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 74,
+   "execution_count": 94,
    "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "[array([[-0.23215847]], dtype=float32), array([15.042496], dtype=float32)]\n"
+      "[array([[-0.23217289]], dtype=float32), array([15.043545], dtype=float32)]\n"
      ]
     }
    ],
@@ -836,7 +828,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 75,
+   "execution_count": 95,
    "metadata": {},
    "outputs": [
     {
@@ -849,7 +841,7 @@
     },
     {
      "data": {
-      "image/png": "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\n",
+      "image/png": "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\n",
       "text/plain": [
        "<Figure size 432x288 with 1 Axes>"
       ]
@@ -883,9 +875,27 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 96,
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "1/1 [==============================] - 0s 118ms/step - loss: 0.4416 - accuracy: 0.8696\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "[0.4416346251964569, 0.8695651888847351]"
+      ]
+     },
+     "execution_count": 96,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
    "source": [
     "model.evaluate(x, y)"
    ]
@@ -894,7 +904,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "The value of the cross-entropy loss function could be decreased from "
+    "The value of the cross-entropy loss function could be decreased from 0.9094435 to 0.4416346251964569"
    ]
   },
   {
@@ -915,38 +925,43 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "## TODO : read MNIST data and compute validation accuracy for the multinomial logistic regression model"
+    "## TODO : read MNIST data and compute validation accuracy for a multinomial logistic regression model, see [Multinomial Logistic Regression](https://en.wikipedia.org/wiki/Multinomial_logistic_regression)\n",
+    "\n",
+    "If there are several labels, then we use `categorical_crossentropy` as loss function and the output layer should be a `softmax` layer."
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 24,
+   "execution_count": 97,
    "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
+      "Downloading data from https://storage.googleapis.com/tensorflow/tf-keras-datasets/mnist.npz\n",
+      "11493376/11490434 [==============================] - 0s 0us/step\n",
+      "11501568/11490434 [==============================] - 0s 0us/step\n",
       "Epoch 1/10\n",
-      "1875/1875 [==============================] - 9s 5ms/step - loss: 321.2496 - accuracy: 0.8419 - val_loss: 243.0990 - val_accuracy: 0.8799\n",
+      "1875/1875 [==============================] - 9s 5ms/step - loss: 320.4593 - accuracy: 0.8417 - val_loss: 242.9400 - val_accuracy: 0.8801\n",
       "Epoch 2/10\n",
-      "1875/1875 [==============================] - 9s 5ms/step - loss: 263.8232 - accuracy: 0.8672 - val_loss: 203.2465 - val_accuracy: 0.8986\n",
+      "1875/1875 [==============================] - 8s 4ms/step - loss: 257.2356 - accuracy: 0.8691 - val_loss: 381.1338 - val_accuracy: 0.8126\n",
       "Epoch 3/10\n",
-      "1875/1875 [==============================] - 9s 5ms/step - loss: 253.0255 - accuracy: 0.8741 - val_loss: 208.3061 - val_accuracy: 0.8858\n",
+      "1875/1875 [==============================] - 8s 5ms/step - loss: 246.9380 - accuracy: 0.8741 - val_loss: 225.4031 - val_accuracy: 0.8802\n",
       "Epoch 4/10\n",
-      "1875/1875 [==============================] - 8s 4ms/step - loss: 247.8131 - accuracy: 0.8757 - val_loss: 522.1936 - val_accuracy: 0.7770\n",
+      "1875/1875 [==============================] - 8s 4ms/step - loss: 238.4442 - accuracy: 0.8784 - val_loss: 312.3720 - val_accuracy: 0.8513\n",
       "Epoch 5/10\n",
-      "1875/1875 [==============================] - 8s 4ms/step - loss: 244.3168 - accuracy: 0.8773 - val_loss: 264.0963 - val_accuracy: 0.8677\n",
+      "1875/1875 [==============================] - 9s 5ms/step - loss: 238.5885 - accuracy: 0.8783 - val_loss: 195.5100 - val_accuracy: 0.9018\n",
       "Epoch 6/10\n",
-      "1875/1875 [==============================] - 9s 5ms/step - loss: 239.8172 - accuracy: 0.8792 - val_loss: 251.0652 - val_accuracy: 0.8803\n",
+      "1875/1875 [==============================] - 9s 5ms/step - loss: 238.2655 - accuracy: 0.8773 - val_loss: 253.4705 - val_accuracy: 0.8795\n",
       "Epoch 7/10\n",
-      "1875/1875 [==============================] - 8s 4ms/step - loss: 243.0666 - accuracy: 0.8798 - val_loss: 245.4965 - val_accuracy: 0.8903\n",
+      "1875/1875 [==============================] - 9s 5ms/step - loss: 237.9472 - accuracy: 0.8798 - val_loss: 250.7999 - val_accuracy: 0.8824\n",
       "Epoch 8/10\n",
-      "1875/1875 [==============================] - 8s 4ms/step - loss: 236.9614 - accuracy: 0.8811 - val_loss: 270.9126 - val_accuracy: 0.8773\n",
+      "1875/1875 [==============================] - 8s 5ms/step - loss: 237.2793 - accuracy: 0.8802 - val_loss: 285.5836 - val_accuracy: 0.8707\n",
       "Epoch 9/10\n",
-      "1875/1875 [==============================] - 8s 4ms/step - loss: 235.9632 - accuracy: 0.8825 - val_loss: 208.9754 - val_accuracy: 0.8894\n",
+      "1875/1875 [==============================] - 8s 4ms/step - loss: 235.1660 - accuracy: 0.8808 - val_loss: 277.7219 - val_accuracy: 0.8809\n",
       "Epoch 10/10\n",
-      "1875/1875 [==============================] - 8s 4ms/step - loss: 229.1799 - accuracy: 0.8818 - val_loss: 288.4063 - val_accuracy: 0.8719\n"
+      "1875/1875 [==============================] - 9s 5ms/step - loss: 233.3158 - accuracy: 0.8822 - val_loss: 263.0470 - val_accuracy: 0.8765\n"
      ]
     }
    ],
@@ -986,15 +1001,15 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 25,
+   "execution_count": 98,
    "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "313/313 [==============================] - 1s 4ms/step - loss: 288.4063 - accuracy: 0.8719\n",
-      "Accuracy on test dataset: 0.8719000220298767\n"
+      "313/313 [==============================] - 1s 4ms/step - loss: 263.0470 - accuracy: 0.8765\n",
+      "Accuracy on test dataset: 0.8765000104904175\n"
      ]
     }
    ],
@@ -1012,7 +1027,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 26,
+   "execution_count": 99,
    "metadata": {},
    "outputs": [
     {
@@ -1020,25 +1035,25 @@
      "output_type": "stream",
      "text": [
       "Epoch 1/10\n",
-      "1875/1875 [==============================] - 10s 5ms/step - loss: 333.7498 - accuracy: 0.8395 - val_loss: 261.9417 - val_accuracy: 0.8583\n",
+      "1875/1875 [==============================] - 9s 5ms/step - loss: 338.3148 - accuracy: 0.8376 - val_loss: 217.6844 - val_accuracy: 0.8881\n",
       "Epoch 2/10\n",
-      "1875/1875 [==============================] - 9s 5ms/step - loss: 291.4153 - accuracy: 0.8573 - val_loss: 244.7811 - val_accuracy: 0.8729\n",
+      "1875/1875 [==============================] - 9s 5ms/step - loss: 287.3254 - accuracy: 0.8573 - val_loss: 281.7627 - val_accuracy: 0.8726\n",
       "Epoch 3/10\n",
-      "1875/1875 [==============================] - 8s 4ms/step - loss: 282.5951 - accuracy: 0.8601 - val_loss: 412.3524 - val_accuracy: 0.8189\n",
+      "1875/1875 [==============================] - 9s 5ms/step - loss: 288.3959 - accuracy: 0.8602 - val_loss: 320.5165 - val_accuracy: 0.8475\n",
       "Epoch 4/10\n",
-      "1875/1875 [==============================] - 9s 5ms/step - loss: 289.8486 - accuracy: 0.8601 - val_loss: 258.7878 - val_accuracy: 0.8644\n",
+      "1875/1875 [==============================] - 9s 5ms/step - loss: 296.8785 - accuracy: 0.8590 - val_loss: 222.1539 - val_accuracy: 0.8899\n",
       "Epoch 5/10\n",
-      "1875/1875 [==============================] - 8s 4ms/step - loss: 279.0330 - accuracy: 0.8620 - val_loss: 324.4070 - val_accuracy: 0.8390\n",
+      "1875/1875 [==============================] - 9s 5ms/step - loss: 283.6608 - accuracy: 0.8618 - val_loss: 460.9875 - val_accuracy: 0.8016\n",
       "Epoch 6/10\n",
-      "1875/1875 [==============================] - 9s 5ms/step - loss: 285.5763 - accuracy: 0.8607 - val_loss: 223.8089 - val_accuracy: 0.8819\n",
+      "1875/1875 [==============================] - 9s 5ms/step - loss: 277.9357 - accuracy: 0.8639 - val_loss: 245.5682 - val_accuracy: 0.8875\n",
       "Epoch 7/10\n",
-      "1875/1875 [==============================] - 9s 5ms/step - loss: 278.4053 - accuracy: 0.8630 - val_loss: 241.8423 - val_accuracy: 0.8798\n",
+      "1875/1875 [==============================] - 9s 5ms/step - loss: 287.6865 - accuracy: 0.8610 - val_loss: 252.3817 - val_accuracy: 0.8678\n",
       "Epoch 8/10\n",
-      "1875/1875 [==============================] - 9s 5ms/step - loss: 287.0358 - accuracy: 0.8609 - val_loss: 278.3787 - val_accuracy: 0.8620\n",
+      "1875/1875 [==============================] - 9s 5ms/step - loss: 284.3436 - accuracy: 0.8620 - val_loss: 228.4689 - val_accuracy: 0.8884\n",
       "Epoch 9/10\n",
-      "1875/1875 [==============================] - 8s 4ms/step - loss: 284.3555 - accuracy: 0.8619 - val_loss: 321.4152 - val_accuracy: 0.8505\n",
+      "1875/1875 [==============================] - 9s 5ms/step - loss: 282.4845 - accuracy: 0.8623 - val_loss: 258.1628 - val_accuracy: 0.8879\n",
       "Epoch 10/10\n",
-      "1875/1875 [==============================] - 9s 5ms/step - loss: 282.8943 - accuracy: 0.8621 - val_loss: 218.7821 - val_accuracy: 0.8939\n"
+      "1875/1875 [==============================] - 9s 5ms/step - loss: 285.5985 - accuracy: 0.8620 - val_loss: 484.2548 - val_accuracy: 0.7784\n"
      ]
     }
    ],
@@ -1080,15 +1095,15 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 27,
+   "execution_count": 100,
    "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "313/313 [==============================] - 1s 4ms/step - loss: 218.7821 - accuracy: 0.8939\n",
-      "Accuracy on test dataset: 0.8938999772071838\n"
+      "313/313 [==============================] - 1s 3ms/step - loss: 484.2548 - accuracy: 0.7784\n",
+      "Accuracy on test dataset: 0.7784000039100647\n"
      ]
     }
    ],