diff --git a/11_training_deep_neural_networks.ipynb b/11_training_deep_neural_networks.ipynb
index 2a0691eeb..8c05b246b 100644
--- a/11_training_deep_neural_networks.ipynb
+++ b/11_training_deep_neural_networks.ipynb
@@ -405,41 +405,31 @@
     "scrolled": true
    },
    "outputs": [
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "WARNING: Logging before flag parsing goes to stderr.\n",
-      "W0610 10:46:09.866298 140735810999168 deprecation.py:323] From /Users/ageron/miniconda3/envs/tf2/lib/python3.6/site-packages/tensorflow/python/ops/math_grad.py:1251: add_dispatch_support.<locals>.wrapper (from tensorflow.python.ops.array_ops) is deprecated and will be removed in a future version.\n",
-      "Instructions for updating:\n",
-      "Use tf.where in 2.0, which has the same broadcast rule as np.where\n"
-     ]
-    },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
       "Train on 55000 samples, validate on 5000 samples\n",
       "Epoch 1/10\n",
-      "55000/55000 [==============================] - 3s 57us/sample - loss: 1.2810 - accuracy: 0.6253 - val_loss: 0.8872 - val_accuracy: 0.7192\n",
+      "55000/55000 [==============================] - 3s 50us/sample - loss: 1.2806 - accuracy: 0.6250 - val_loss: 0.8883 - val_accuracy: 0.7152\n",
       "Epoch 2/10\n",
-      "55000/55000 [==============================] - 3s 54us/sample - loss: 0.7957 - accuracy: 0.7371 - val_loss: 0.7128 - val_accuracy: 0.7676\n",
+      "55000/55000 [==============================] - 2s 40us/sample - loss: 0.7954 - accuracy: 0.7373 - val_loss: 0.7135 - val_accuracy: 0.7648\n",
       "Epoch 3/10\n",
-      "55000/55000 [==============================] - 3s 54us/sample - loss: 0.6818 - accuracy: 0.7720 - val_loss: 0.6365 - val_accuracy: 0.7902\n",
+      "55000/55000 [==============================] - 2s 42us/sample - loss: 0.6816 - accuracy: 0.7727 - val_loss: 0.6356 - val_accuracy: 0.7882\n",
       "Epoch 4/10\n",
-      "55000/55000 [==============================] - 3s 54us/sample - loss: 0.6221 - accuracy: 0.7934 - val_loss: 0.5898 - val_accuracy: 0.8082\n",
+      "55000/55000 [==============================] - 2s 42us/sample - loss: 0.6215 - accuracy: 0.7935 - val_loss: 0.5922 - val_accuracy: 0.8012\n",
       "Epoch 5/10\n",
-      "55000/55000 [==============================] - 3s 54us/sample - loss: 0.5831 - accuracy: 0.8066 - val_loss: 0.5584 - val_accuracy: 0.8166\n",
+      "55000/55000 [==============================] - 2s 42us/sample - loss: 0.5830 - accuracy: 0.8081 - val_loss: 0.5596 - val_accuracy: 0.8172\n",
       "Epoch 6/10\n",
-      "55000/55000 [==============================] - 3s 53us/sample - loss: 0.5553 - accuracy: 0.8165 - val_loss: 0.5358 - val_accuracy: 0.8246\n",
+      "55000/55000 [==============================] - 2s 42us/sample - loss: 0.5553 - accuracy: 0.8155 - val_loss: 0.5338 - val_accuracy: 0.8240\n",
       "Epoch 7/10\n",
-      "55000/55000 [==============================] - 3s 53us/sample - loss: 0.5341 - accuracy: 0.8218 - val_loss: 0.5177 - val_accuracy: 0.8284\n",
+      "55000/55000 [==============================] - 2s 40us/sample - loss: 0.5340 - accuracy: 0.8221 - val_loss: 0.5157 - val_accuracy: 0.8310\n",
       "Epoch 8/10\n",
-      "55000/55000 [==============================] - 3s 52us/sample - loss: 0.5174 - accuracy: 0.8271 - val_loss: 0.5018 - val_accuracy: 0.8374\n",
+      "55000/55000 [==============================] - 2s 41us/sample - loss: 0.5172 - accuracy: 0.8265 - val_loss: 0.5035 - val_accuracy: 0.8336\n",
       "Epoch 9/10\n",
-      "55000/55000 [==============================] - 3s 54us/sample - loss: 0.5038 - accuracy: 0.8303 - val_loss: 0.4901 - val_accuracy: 0.8382\n",
+      "55000/55000 [==============================] - 2s 42us/sample - loss: 0.5036 - accuracy: 0.8299 - val_loss: 0.4950 - val_accuracy: 0.8354\n",
       "Epoch 10/10\n",
-      "55000/55000 [==============================] - 3s 58us/sample - loss: 0.4926 - accuracy: 0.8326 - val_loss: 0.4830 - val_accuracy: 0.8392\n"
+      "55000/55000 [==============================] - 2s 42us/sample - loss: 0.4922 - accuracy: 0.8324 - val_loss: 0.4797 - val_accuracy: 0.8430\n"
      ]
     }
    ],
@@ -2768,12 +2758,13 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "55000/55000 [==============================] - 2s 29us/sample - loss: nan - accuracy: 0.3973\n"
+      "Train on 55000 samples\n",
+      "55000/55000 [==============================] - 2s 28us/sample - loss: nan - accuracy: 0.3888\n"
      ]
     },
     {
      "data": {
-      "image/png": "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\n",
+      "image/png": "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\n",
       "text/plain": [
        "<Figure size 432x288 with 1 Axes>"
       ]
@@ -2807,7 +2798,7 @@
     "        self.last_rate = last_rate or self.start_rate / 1000\n",
     "        self.iteration = 0\n",
     "    def _interpolate(self, iter1, iter2, rate1, rate2):\n",
-    "        return ((rate2 - rate1) * (iter2 - self.iteration)\n",
+    "        return ((rate2 - rate1) * (self.iteration - iter1)\n",
     "                / (iter2 - iter1) + rate1)\n",
     "    def on_batch_begin(self, batch, logs):\n",
     "        if self.iteration < self.half_iteration:\n",
@@ -2834,55 +2825,55 @@
      "text": [
       "Train on 55000 samples, validate on 5000 samples\n",
       "Epoch 1/25\n",
-      "55000/55000 [==============================] - 2s 30us/sample - loss: 0.4926 - accuracy: 0.8268 - val_loss: 0.4229 - val_accuracy: 0.8520\n",
+      "55000/55000 [==============================] - 1s 23us/sample - loss: 0.6569 - accuracy: 0.7750 - val_loss: 0.4875 - val_accuracy: 0.8300\n",
       "Epoch 2/25\n",
-      "55000/55000 [==============================] - 1s 27us/sample - loss: 0.3754 - accuracy: 0.8669 - val_loss: 0.3833 - val_accuracy: 0.8634\n",
+      "55000/55000 [==============================] - 1s 22us/sample - loss: 0.4584 - accuracy: 0.8391 - val_loss: 0.4390 - val_accuracy: 0.8476\n",
       "Epoch 3/25\n",
-      "55000/55000 [==============================] - 1s 26us/sample - loss: 0.3433 - accuracy: 0.8776 - val_loss: 0.3687 - val_accuracy: 0.8666\n",
+      "55000/55000 [==============================] - 1s 21us/sample - loss: 0.4124 - accuracy: 0.8541 - val_loss: 0.4102 - val_accuracy: 0.8570\n",
       "Epoch 4/25\n",
-      "55000/55000 [==============================] - 2s 28us/sample - loss: 0.3198 - accuracy: 0.8854 - val_loss: 0.3595 - val_accuracy: 0.8738\n",
+      "55000/55000 [==============================] - 1s 22us/sample - loss: 0.3842 - accuracy: 0.8643 - val_loss: 0.3893 - val_accuracy: 0.8652\n",
       "Epoch 5/25\n",
-      "55000/55000 [==============================] - 1s 26us/sample - loss: 0.3011 - accuracy: 0.8920 - val_loss: 0.3421 - val_accuracy: 0.8764\n",
+      "55000/55000 [==============================] - 1s 21us/sample - loss: 0.3641 - accuracy: 0.8707 - val_loss: 0.3736 - val_accuracy: 0.8678\n",
       "Epoch 6/25\n",
-      "55000/55000 [==============================] - 1s 26us/sample - loss: 0.2873 - accuracy: 0.8973 - val_loss: 0.3371 - val_accuracy: 0.8814\n",
+      "55000/55000 [==============================] - 1s 22us/sample - loss: 0.3456 - accuracy: 0.8781 - val_loss: 0.3652 - val_accuracy: 0.8726\n",
       "Epoch 7/25\n",
-      "55000/55000 [==============================] - 1s 27us/sample - loss: 0.2738 - accuracy: 0.9026 - val_loss: 0.3312 - val_accuracy: 0.8842\n",
+      "55000/55000 [==============================] - 1s 23us/sample - loss: 0.3318 - accuracy: 0.8818 - val_loss: 0.3596 - val_accuracy: 0.8768\n",
       "Epoch 8/25\n",
-      "55000/55000 [==============================] - 2s 28us/sample - loss: 0.2633 - accuracy: 0.9071 - val_loss: 0.3338 - val_accuracy: 0.8824\n",
+      "55000/55000 [==============================] - 1s 24us/sample - loss: 0.3180 - accuracy: 0.8862 - val_loss: 0.3845 - val_accuracy: 0.8602\n",
       "Epoch 9/25\n",
-      "55000/55000 [==============================] - 1s 26us/sample - loss: 0.2543 - accuracy: 0.9098 - val_loss: 0.3296 - val_accuracy: 0.8840\n",
+      "55000/55000 [==============================] - 1s 23us/sample - loss: 0.3062 - accuracy: 0.8893 - val_loss: 0.3824 - val_accuracy: 0.8660\n",
       "Epoch 10/25\n",
-      "55000/55000 [==============================] - 1s 27us/sample - loss: 0.2465 - accuracy: 0.9125 - val_loss: 0.3233 - val_accuracy: 0.8874\n",
+      "55000/55000 [==============================] - 1s 23us/sample - loss: 0.2938 - accuracy: 0.8934 - val_loss: 0.3516 - val_accuracy: 0.8742\n",
       "Epoch 11/25\n",
-      "55000/55000 [==============================] - 1s 26us/sample - loss: 0.2406 - accuracy: 0.9157 - val_loss: 0.3215 - val_accuracy: 0.8874\n",
+      "55000/55000 [==============================] - 1s 23us/sample - loss: 0.2838 - accuracy: 0.8975 - val_loss: 0.3609 - val_accuracy: 0.8740\n",
       "Epoch 12/25\n",
-      "55000/55000 [==============================] - 1s 27us/sample - loss: 0.2366 - accuracy: 0.9173 - val_loss: 0.3237 - val_accuracy: 0.8862\n",
+      "55000/55000 [==============================] - 1s 23us/sample - loss: 0.2716 - accuracy: 0.9025 - val_loss: 0.3843 - val_accuracy: 0.8666\n",
       "Epoch 13/25\n",
-      "55000/55000 [==============================] - 2s 27us/sample - loss: 0.2370 - accuracy: 0.9160 - val_loss: 0.3282 - val_accuracy: 0.8856\n",
+      "55000/55000 [==============================] - 1s 22us/sample - loss: 0.2541 - accuracy: 0.9091 - val_loss: 0.3282 - val_accuracy: 0.8844\n",
       "Epoch 14/25\n",
-      "55000/55000 [==============================] - 1s 27us/sample - loss: 0.2366 - accuracy: 0.9157 - val_loss: 0.3228 - val_accuracy: 0.8874\n",
+      "55000/55000 [==============================] - 1s 22us/sample - loss: 0.2390 - accuracy: 0.9139 - val_loss: 0.3336 - val_accuracy: 0.8838\n",
       "Epoch 15/25\n",
-      "55000/55000 [==============================] - 1s 27us/sample - loss: 0.2362 - accuracy: 0.9162 - val_loss: 0.3261 - val_accuracy: 0.8860\n",
+      "55000/55000 [==============================] - 1s 23us/sample - loss: 0.2273 - accuracy: 0.9177 - val_loss: 0.3283 - val_accuracy: 0.8884\n",
       "Epoch 16/25\n",
-      "55000/55000 [==============================] - 2s 28us/sample - loss: 0.2339 - accuracy: 0.9167 - val_loss: 0.3336 - val_accuracy: 0.8830\n",
+      "55000/55000 [==============================] - 1s 22us/sample - loss: 0.2156 - accuracy: 0.9234 - val_loss: 0.3288 - val_accuracy: 0.8862\n",
       "Epoch 17/25\n",
-      "55000/55000 [==============================] - 1s 27us/sample - loss: 0.2319 - accuracy: 0.9166 - val_loss: 0.3316 - val_accuracy: 0.8818\n",
+      "55000/55000 [==============================] - 1s 26us/sample - loss: 0.2062 - accuracy: 0.9265 - val_loss: 0.3215 - val_accuracy: 0.8896\n",
       "Epoch 18/25\n",
-      "55000/55000 [==============================] - 1s 26us/sample - loss: 0.2295 - accuracy: 0.9181 - val_loss: 0.3424 - val_accuracy: 0.8786\n",
+      "55000/55000 [==============================] - 1s 24us/sample - loss: 0.1973 - accuracy: 0.9299 - val_loss: 0.3284 - val_accuracy: 0.8912\n",
       "Epoch 19/25\n",
-      "55000/55000 [==============================] - 1s 27us/sample - loss: 0.2266 - accuracy: 0.9186 - val_loss: 0.3356 - val_accuracy: 0.8844\n",
+      "55000/55000 [==============================] - 1s 22us/sample - loss: 0.1892 - accuracy: 0.9344 - val_loss: 0.3229 - val_accuracy: 0.8904\n",
       "Epoch 20/25\n",
-      "55000/55000 [==============================] - 1s 27us/sample - loss: 0.2250 - accuracy: 0.9186 - val_loss: 0.3486 - val_accuracy: 0.8758\n",
+      "55000/55000 [==============================] - 1s 22us/sample - loss: 0.1822 - accuracy: 0.9366 - val_loss: 0.3196 - val_accuracy: 0.8902\n",
       "Epoch 21/25\n",
-      "55000/55000 [==============================] - 1s 27us/sample - loss: 0.2221 - accuracy: 0.9189 - val_loss: 0.3443 - val_accuracy: 0.8856\n",
+      "55000/55000 [==============================] - 1s 24us/sample - loss: 0.1758 - accuracy: 0.9388 - val_loss: 0.3184 - val_accuracy: 0.8940\n",
       "Epoch 22/25\n",
-      "55000/55000 [==============================] - 1s 27us/sample - loss: 0.2184 - accuracy: 0.9201 - val_loss: 0.3889 - val_accuracy: 0.8700\n",
+      "55000/55000 [==============================] - 1s 27us/sample - loss: 0.1699 - accuracy: 0.9422 - val_loss: 0.3221 - val_accuracy: 0.8912\n",
       "Epoch 23/25\n",
-      "55000/55000 [==============================] - 1s 27us/sample - loss: 0.2040 - accuracy: 0.9266 - val_loss: 0.3216 - val_accuracy: 0.8910\n",
+      "55000/55000 [==============================] - 1s 26us/sample - loss: 0.1657 - accuracy: 0.9444 - val_loss: 0.3173 - val_accuracy: 0.8944\n",
       "Epoch 24/25\n",
-      "55000/55000 [==============================] - 2s 28us/sample - loss: 0.1750 - accuracy: 0.9401 - val_loss: 0.3153 - val_accuracy: 0.8932\n",
+      "55000/55000 [==============================] - 1s 23us/sample - loss: 0.1630 - accuracy: 0.9457 - val_loss: 0.3162 - val_accuracy: 0.8946\n",
       "Epoch 25/25\n",
-      "55000/55000 [==============================] - 2s 28us/sample - loss: 0.1718 - accuracy: 0.9416 - val_loss: 0.3153 - val_accuracy: 0.8940\n"
+      "55000/55000 [==============================] - 1s 26us/sample - loss: 0.1610 - accuracy: 0.9464 - val_loss: 0.3169 - val_accuracy: 0.8942\n"
      ]
     }
    ],
@@ -4233,7 +4224,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.6.8"
+   "version": "3.7.4"
   },
   "nav_menu": {
    "height": "360px",