diff --git a/11_training_deep_neural_networks.ipynb b/11_training_deep_neural_networks.ipynb
index a9c7f98..2c84527 100644
--- a/11_training_deep_neural_networks.ipynb
+++ b/11_training_deep_neural_networks.ipynb
@@ -791,7 +791,7 @@
    "source": [
     "# extra code – just show that the model works! 😊\n",
     "model.compile(loss=\"sparse_categorical_crossentropy\", optimizer=\"sgd\",\n",
-    "              metrics=\"accuracy\")\n",
+    "              metrics=[\"accuracy\"])\n",
     "model.fit(X_train, y_train, epochs=2, validation_data=(X_valid, y_valid))"
    ]
   },
@@ -860,7 +860,7 @@
    "source": [
     "# extra code – just show that the model works! 😊\n",
     "model.compile(loss=\"sparse_categorical_crossentropy\", optimizer=\"sgd\",\n",
-    "              metrics=\"accuracy\")\n",
+    "              metrics=[\"accuracy\"])\n",
     "model.fit(X_train, y_train, epochs=2, validation_data=(X_valid, y_valid))"
    ]
   },
@@ -1031,7 +1031,7 @@
     "                metrics=[\"accuracy\"])\n",
     "history = model_A.fit(X_train_A, y_train_A, epochs=20,\n",
     "                      validation_data=(X_valid_A, y_valid_A))\n",
-    "model_A.save(\"my_model_A\")"
+    "model_A.save(\"my_model_A.keras\")"
    ]
   },
   {
@@ -1133,7 +1133,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "model_A = tf.keras.models.load_model(\"my_model_A\")\n",
+    "model_A = tf.keras.models.load_model(\"my_model_A.keras\")\n",
     "model_B_on_A = tf.keras.Sequential(model_A.layers[:-1])\n",
     "model_B_on_A.add(tf.keras.layers.Dense(1, activation=\"sigmoid\"))"
    ]
@@ -1910,7 +1910,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "**Note**: The `decay` argument in optimizers is deprecated. The old optimizers which implement the `decay` argument are still available in `tf.keras.optimizers.legacy`, but you should use the schedulers in `tf.keras.optimizers.schedules` instead."
+    "**Note**: Optimizers used to have a `decay` argument for this, but it was deprecated. You must use the schedulers in `tf.keras.optimizers.schedules` instead."
    ]
   },
   {
@@ -1919,17 +1919,6 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "# DEPRECATED:\n",
-    "optimizer = tf.keras.optimizers.legacy.SGD(learning_rate=0.01, decay=1e-4)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 66,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# RECOMMENDED:\n",
     "lr_schedule = tf.keras.optimizers.schedules.InverseTimeDecay(\n",
     "    initial_learning_rate=0.01,\n",
     "    decay_steps=10_000,\n",
@@ -1948,7 +1937,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 67,
+   "execution_count": 66,
    "metadata": {},
    "outputs": [
     {
@@ -1984,7 +1973,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 68,
+   "execution_count": 67,
    "metadata": {},
    "outputs": [
     {
@@ -2038,7 +2027,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 69,
+   "execution_count": 68,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -2053,7 +2042,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 70,
+   "execution_count": 69,
    "metadata": {},
    "outputs": [
     {
@@ -2089,7 +2078,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 71,
+   "execution_count": 70,
    "metadata": {},
    "outputs": [
     {
@@ -2134,7 +2123,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 72,
+   "execution_count": 71,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -2144,7 +2133,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 73,
+   "execution_count": 72,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -2158,7 +2147,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 74,
+   "execution_count": 73,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -2173,7 +2162,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 75,
+   "execution_count": 74,
    "metadata": {
     "scrolled": true
    },
@@ -2253,7 +2242,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 76,
+   "execution_count": 75,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -2270,7 +2259,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 77,
+   "execution_count": 76,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -2283,18 +2272,18 @@
     "\n",
     "    def on_batch_begin(self, batch, logs=None):\n",
     "        # Note: the `batch` argument is reset at each epoch\n",
-    "        lr = K.get_value(self.model.optimizer.learning_rate)\n",
+    "        lr = self.model.optimizer.learning_rate.numpy()\n",
     "        new_learning_rate = lr * 0.1 ** (1 / self.n_steps)\n",
-    "        K.set_value(self.model.optimizer.learning_rate, new_learning_rate)\n",
+    "        self.model.optimizer.learning_rate = new_learning_rate\n",
     "\n",
     "    def on_epoch_end(self, epoch, logs=None):\n",
     "        logs = logs or {}\n",
-    "        logs['lr'] = K.get_value(self.model.optimizer.learning_rate)"
+    "        logs['lr'] = self.model.optimizer.learning_rate.numpy()"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 78,
+   "execution_count": 77,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -2307,7 +2296,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 79,
+   "execution_count": 78,
    "metadata": {},
    "outputs": [
     {
@@ -2387,7 +2376,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 80,
+   "execution_count": 79,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -2400,7 +2389,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 81,
+   "execution_count": 80,
    "metadata": {},
    "outputs": [
     {
@@ -2436,7 +2425,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 82,
+   "execution_count": 81,
    "metadata": {
     "scrolled": true
    },
@@ -2482,7 +2471,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 83,
+   "execution_count": 82,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -2497,7 +2486,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 84,
+   "execution_count": 83,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -2516,7 +2505,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 85,
+   "execution_count": 84,
    "metadata": {},
    "outputs": [
     {
@@ -2601,7 +2590,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 86,
+   "execution_count": 85,
    "metadata": {},
    "outputs": [
     {
@@ -2635,7 +2624,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 87,
+   "execution_count": 86,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -2649,7 +2638,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 88,
+   "execution_count": 87,
    "metadata": {},
    "outputs": [
     {
@@ -2718,7 +2707,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 89,
+   "execution_count": 88,
    "metadata": {},
    "outputs": [
     {
@@ -2737,7 +2726,7 @@
    "source": [
     "# extra code – this cell plots performance scheduling\n",
     "\n",
-    "plt.plot(history.epoch, history.history[\"lr\"], \"bo-\")\n",
+    "plt.plot(history.epoch, history.history[\"learning_rate\"], \"bo-\")\n",
     "plt.xlabel(\"Epoch\")\n",
     "plt.ylabel(\"Learning Rate\", color='b')\n",
     "plt.tick_params('y', colors='b')\n",
@@ -2769,7 +2758,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 90,
+   "execution_count": 89,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -2789,10 +2778,10 @@
     "        new_sum_of_epoch_losses = mean_epoch_loss * (batch + 1)\n",
     "        batch_loss = new_sum_of_epoch_losses - self.sum_of_epoch_losses\n",
     "        self.sum_of_epoch_losses = new_sum_of_epoch_losses\n",
-    "        self.rates.append(K.get_value(self.model.optimizer.learning_rate))\n",
+    "        lr = self.model.optimizer.learning_rate.numpy()\n",
+    "        self.rates.append(lr)\n",
     "        self.losses.append(batch_loss)\n",
-    "        K.set_value(self.model.optimizer.learning_rate,\n",
-    "                    self.model.optimizer.learning_rate * self.factor)"
+    "        self.model.optimizer.learning_rate = lr * self.factor"
    ]
   },
   {
@@ -2804,7 +2793,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 91,
+   "execution_count": 90,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -2814,11 +2803,11 @@
     "    iterations = math.ceil(len(X) / batch_size) * epochs\n",
     "    factor = (max_rate / min_rate) ** (1 / iterations)\n",
     "    init_lr = K.get_value(model.optimizer.learning_rate)\n",
-    "    K.set_value(model.optimizer.learning_rate, min_rate)\n",
+    "    model.optimizer.learning_rate = min_rate\n",
     "    exp_lr = ExponentialLearningRate(factor)\n",
     "    history = model.fit(X, y, epochs=epochs, batch_size=batch_size,\n",
     "                        callbacks=[exp_lr])\n",
-    "    K.set_value(model.optimizer.learning_rate, init_lr)\n",
+    "    model.optimizer.learning_rate = init_lr\n",
     "    model.set_weights(init_weights)\n",
     "    return exp_lr.rates, exp_lr.losses"
    ]
@@ -2832,7 +2821,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 92,
+   "execution_count": 91,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -2856,7 +2845,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 93,
+   "execution_count": 92,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -2875,7 +2864,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 94,
+   "execution_count": 93,
    "metadata": {},
    "outputs": [
     {
@@ -2921,7 +2910,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 95,
+   "execution_count": 94,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -2950,7 +2939,7 @@
     "            lr = self._interpolate(2 * self.half_iteration, self.iterations,\n",
     "                                   self.start_lr, self.last_lr)\n",
     "        self.iteration += 1\n",
-    "        K.set_value(self.model.optimizer.learning_rate, lr)"
+    "        self.model.optimizer.learning_rate = lr"
    ]
   },
   {
@@ -2962,7 +2951,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 96,
+   "execution_count": 95,
    "metadata": {},
    "outputs": [
     {
@@ -3051,7 +3040,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 97,
+   "execution_count": 96,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -3069,7 +3058,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 98,
+   "execution_count": 97,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -3078,7 +3067,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 99,
+   "execution_count": 98,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -3099,7 +3088,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 100,
+   "execution_count": 99,
    "metadata": {},
    "outputs": [
     {
@@ -3131,7 +3120,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 101,
+   "execution_count": 100,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -3140,7 +3129,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 102,
+   "execution_count": 101,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -3159,7 +3148,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 103,
+   "execution_count": 102,
    "metadata": {},
    "outputs": [
     {
@@ -3207,7 +3196,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 104,
+   "execution_count": 103,
    "metadata": {},
    "outputs": [
     {
@@ -3223,7 +3212,7 @@
        "[0.30816400051116943, 0.8849090933799744]"
       ]
      },
-     "execution_count": 104,
+     "execution_count": 103,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -3234,7 +3223,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 105,
+   "execution_count": 104,
    "metadata": {},
    "outputs": [
     {
@@ -3250,7 +3239,7 @@
        "[0.3628920316696167, 0.8700000047683716]"
       ]
      },
-     "execution_count": 105,
+     "execution_count": 104,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -3275,7 +3264,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 106,
+   "execution_count": 105,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -3284,7 +3273,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 107,
+   "execution_count": 106,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -3295,7 +3284,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 108,
+   "execution_count": 107,
    "metadata": {},
    "outputs": [
     {
@@ -3305,7 +3294,7 @@
        "        0.844]], dtype=float32)"
       ]
      },
-     "execution_count": 108,
+     "execution_count": 107,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -3316,7 +3305,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 109,
+   "execution_count": 108,
    "metadata": {},
    "outputs": [
     {
@@ -3326,7 +3315,7 @@
        "       0.723], dtype=float32)"
       ]
      },
-     "execution_count": 109,
+     "execution_count": 108,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -3337,7 +3326,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 110,
+   "execution_count": 109,
    "metadata": {},
    "outputs": [
     {
@@ -3347,7 +3336,7 @@
        "       0.183], dtype=float32)"
       ]
      },
-     "execution_count": 110,
+     "execution_count": 109,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -3359,7 +3348,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 111,
+   "execution_count": 110,
    "metadata": {},
    "outputs": [
     {
@@ -3368,7 +3357,7 @@
        "0.8717"
       ]
      },
-     "execution_count": 111,
+     "execution_count": 110,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -3381,7 +3370,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 112,
+   "execution_count": 111,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -3392,7 +3381,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 113,
+   "execution_count": 112,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -3407,7 +3396,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 114,
+   "execution_count": 113,
    "metadata": {},
    "outputs": [
     {
@@ -3452,7 +3441,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 115,
+   "execution_count": 114,
    "metadata": {},
    "outputs": [
     {
@@ -3462,7 +3451,7 @@
        "      dtype=float32)"
       ]
      },
-     "execution_count": 115,
+     "execution_count": 114,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -3483,7 +3472,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 116,
+   "execution_count": 115,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -3494,7 +3483,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 117,
+   "execution_count": 116,
    "metadata": {},
    "outputs": [
     {
@@ -3589,7 +3578,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 118,
+   "execution_count": 117,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -3620,7 +3609,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 119,
+   "execution_count": 118,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -3636,7 +3625,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 120,
+   "execution_count": 119,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -3655,7 +3644,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 121,
+   "execution_count": 120,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -3677,13 +3666,13 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 122,
+   "execution_count": 121,
    "metadata": {},
    "outputs": [],
    "source": [
     "early_stopping_cb = tf.keras.callbacks.EarlyStopping(patience=20,\n",
     "                                                     restore_best_weights=True)\n",
-    "model_checkpoint_cb = tf.keras.callbacks.ModelCheckpoint(\"my_cifar10_model\",\n",
+    "model_checkpoint_cb = tf.keras.callbacks.ModelCheckpoint(\"my_cifar10_model.keras\",\n",
     "                                                         save_best_only=True)\n",
     "run_index = 1 # increment every time you train the model\n",
     "run_logdir = Path() / \"my_cifar10_logs\" / f\"run_{run_index:03d}\"\n",
@@ -3693,7 +3682,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 123,
+   "execution_count": 122,
    "metadata": {},
    "outputs": [
     {
@@ -3730,7 +3719,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 124,
+   "execution_count": 123,
    "metadata": {},
    "outputs": [
     {
@@ -3816,7 +3805,7 @@
        "<keras.callbacks.History at 0x7fb9f02fc070>"
       ]
      },
-     "execution_count": 124,
+     "execution_count": 123,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -3829,7 +3818,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 125,
+   "execution_count": 124,
    "metadata": {},
    "outputs": [
     {
@@ -3845,7 +3834,7 @@
        "[1.5061508417129517, 0.4675999879837036]"
       ]
      },
-     "execution_count": 125,
+     "execution_count": 124,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -3882,7 +3871,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 126,
+   "execution_count": 125,
    "metadata": {},
    "outputs": [
     {
@@ -3968,7 +3957,7 @@
        "[1.4236289262771606, 0.5073999762535095]"
       ]
      },
-     "execution_count": 126,
+     "execution_count": 125,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -3992,7 +3981,7 @@
     "\n",
     "early_stopping_cb = tf.keras.callbacks.EarlyStopping(patience=20,\n",
     "                                                     restore_best_weights=True)\n",
-    "model_checkpoint_cb = tf.keras.callbacks.ModelCheckpoint(\"my_cifar10_bn_model\",\n",
+    "model_checkpoint_cb = tf.keras.callbacks.ModelCheckpoint(\"my_cifar10_bn_model.keras\",\n",
     "                                                         save_best_only=True)\n",
     "run_index = 1 # increment every time you train the model\n",
     "run_logdir = Path() / \"my_cifar10_logs\" / f\"run_bn_{run_index:03d}\"\n",
@@ -4025,7 +4014,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 127,
+   "execution_count": 126,
    "metadata": {
     "scrolled": true
    },
@@ -4119,7 +4108,7 @@
        "[1.4607702493667603, 0.5026000142097473]"
       ]
      },
-     "execution_count": 127,
+     "execution_count": 126,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -4144,7 +4133,7 @@
     "early_stopping_cb = tf.keras.callbacks.EarlyStopping(\n",
     "    patience=20, restore_best_weights=True)\n",
     "model_checkpoint_cb = tf.keras.callbacks.ModelCheckpoint(\n",
-    "    \"my_cifar10_selu_model\", save_best_only=True)\n",
+    "    \"my_cifar10_selu_model.keras\", save_best_only=True)\n",
     "run_index = 1 # increment every time you train the model\n",
     "run_logdir = Path() / \"my_cifar10_logs\" / f\"run_selu_{run_index:03d}\"\n",
     "tensorboard_cb = tf.keras.callbacks.TensorBoard(run_logdir)\n",
@@ -4178,6 +4167,22 @@
     "*Exercise: Try regularizing the model with alpha dropout. Then, without retraining your model, see if you can achieve better accuracy using MC Dropout.*"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "**Warning**: there are now two versions of `AlphaDropout`. One is deprecated and also broken in some recent versions of TF, and unfortunately that's the version in the `tensorflow` library. Luckily, there's a perfectly fine version in the `keras` library (i.e., `keras`, not `tf.keras`). It's neither deprecated nor broken, so let's import and use that one:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 127,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import keras.layers.AlphaDropout"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": 128,
@@ -4275,7 +4280,7 @@
     "                                    kernel_initializer=\"lecun_normal\",\n",
     "                                    activation=\"selu\"))\n",
     "\n",
-    "model.add(tf.keras.layers.AlphaDropout(rate=0.1))\n",
+    "model.add(keras.layers.AlphaDropout(rate=0.1))\n",
     "model.add(tf.keras.layers.Dense(10, activation=\"softmax\"))\n",
     "\n",
     "optimizer = tf.keras.optimizers.Nadam(learning_rate=5e-4)\n",
@@ -4286,7 +4291,7 @@
     "early_stopping_cb = tf.keras.callbacks.EarlyStopping(\n",
     "    patience=20, restore_best_weights=True)\n",
     "model_checkpoint_cb = tf.keras.callbacks.ModelCheckpoint(\n",
-    "    \"my_cifar10_alpha_dropout_model\", save_best_only=True)\n",
+    "    \"my_cifar10_alpha_dropout_model.keras\", save_best_only=True)\n",
     "run_index = 1 # increment every time you train the model\n",
     "run_logdir = Path() / \"my_cifar10_logs\" / f\"run_alpha_dropout_{run_index:03d}\"\n",
     "tensorboard_cb = tf.keras.callbacks.TensorBoard(run_logdir)\n",
@@ -4325,7 +4330,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "class MCAlphaDropout(tf.keras.layers.AlphaDropout):\n",
+    "class MCAlphaDropout(keras.layers.AlphaDropout):\n",
     "    def call(self, inputs):\n",
     "        return super().call(inputs, training=True)"
    ]
@@ -4346,7 +4351,7 @@
     "mc_model = tf.keras.Sequential([\n",
     "    (\n",
     "        MCAlphaDropout(layer.rate)\n",
-    "        if isinstance(layer, tf.keras.layers.AlphaDropout)\n",
+    "        if isinstance(layer, keras.layers.AlphaDropout)\n",
     "        else layer\n",
     "    )\n",
     "    for layer in model.layers\n",
@@ -4438,7 +4443,7 @@
     "                                    kernel_initializer=\"lecun_normal\",\n",
     "                                    activation=\"selu\"))\n",
     "\n",
-    "model.add(tf.keras.layers.AlphaDropout(rate=0.1))\n",
+    "model.add(keras.layers.AlphaDropout(rate=0.1))\n",
     "model.add(tf.keras.layers.Dense(10, activation=\"softmax\"))\n",
     "\n",
     "optimizer = tf.keras.optimizers.SGD()\n",
@@ -4494,7 +4499,7 @@
     "                                 kernel_initializer=\"lecun_normal\",\n",
     "                                 activation=\"selu\"))\n",
     "\n",
-    "model.add(tf.keras.layers.AlphaDropout(rate=0.1))\n",
+    "model.add(keras.layers.AlphaDropout(rate=0.1))\n",
     "model.add(tf.keras.layers.Dense(10, activation=\"softmax\"))\n",
     "\n",
     "optimizer = tf.keras.optimizers.SGD(learning_rate=2e-2)\n",
@@ -4564,7 +4569,7 @@
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "Python 3 (ipykernel)",
+   "display_name": "Python 3",
    "language": "python",
    "name": "python3"
   },
@@ -4578,7 +4583,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.13"
+   "version": "3.9.10"
   },
   "nav_menu": {
    "height": "360px",