diff --git a/chapter02_mathematical-building-blocks.ipynb b/chapter02_mathematical-building-blocks.ipynb
index 7a9acbd0de..01edc9becc 100644
--- a/chapter02_mathematical-building-blocks.ipynb
+++ b/chapter02_mathematical-building-blocks.ipynb
@@ -383,7 +383,7 @@
     "colab_type": "text"
    },
    "source": [
-    "### Rank-3 tensors and higher-rank tensors"
+    "### Rank-3 and higher-rank tensors"
    ]
   },
   {
@@ -1028,7 +1028,7 @@
     "colab_type": "text"
    },
    "source": [
-    "### Chaining derivatives: the Backpropagation algorithm"
+    "### Chaining derivatives: The Backpropagation algorithm"
    ]
   },
   {
@@ -1055,7 +1055,7 @@
     "colab_type": "text"
    },
    "source": [
-    "#### The Gradient Tape in TensorFlow"
+    "#### The gradient tape in TensorFlow"
    ]
   },
   {
@@ -1337,7 +1337,7 @@
     "learning_rate = 1e-3\n",
     "\n",
     "def update_weights(gradients, weights):\n",
-    "    for g, w in zip(gradients, model.weights):\n",
+    "    for g, w in zip(gradients, weights):\n",
     "        w.assign_sub(g * learning_rate)"
    ]
   },
@@ -1434,7 +1434,7 @@
     "colab_type": "text"
    },
    "source": [
-    "## Chapter summary"
+    "## Summary"
    ]
   }
  ],
diff --git a/chapter03_introduction-to-keras-and-tf.ipynb b/chapter03_introduction-to-keras-and-tf.ipynb
index 8121203911..69240b5fb2 100644
--- a/chapter03_introduction-to-keras-and-tf.ipynb
+++ b/chapter03_introduction-to-keras-and-tf.ipynb
@@ -42,7 +42,7 @@
     "colab_type": "text"
    },
    "source": [
-    "## Keras and TensorFlow: a brief history"
+    "## Keras and TensorFlow: A brief history"
    ]
   },
   {
@@ -60,7 +60,7 @@
     "colab_type": "text"
    },
    "source": [
-    "### Jupyter notebooks: the preferred way to run deep-learning experiments"
+    "### Jupyter notebooks: The preferred way to run deep-learning experiments"
    ]
   },
   {
@@ -87,7 +87,7 @@
     "colab_type": "text"
    },
    "source": [
-    "#### Installing packages with `pip`"
+    "#### Installing packages with pip"
    ]
   },
   {
@@ -114,7 +114,7 @@
     "colab_type": "text"
    },
    "source": [
-    "#### Constant tensors and Variables"
+    "#### Constant tensors and variables"
    ]
   },
   {
@@ -212,7 +212,7 @@
     "colab_type": "text"
    },
    "source": [
-    "**Creating a Variable**"
+    "**Creating a TensorFlow variable**"
    ]
   },
   {
@@ -233,7 +233,7 @@
     "colab_type": "text"
    },
    "source": [
-    "**Assigning a value to a Variable**"
+    "**Assigning a value to a TensorFlow variable**"
    ]
   },
   {
@@ -253,7 +253,7 @@
     "colab_type": "text"
    },
    "source": [
-    "**Assigning a value to a subset of a Variable**"
+    "**Assigning a value to a subset of a TensorFlow variable**"
    ]
   },
   {
@@ -273,7 +273,7 @@
     "colab_type": "text"
    },
    "source": [
-    "**Using assign_add**"
+    "**Using `assign_add`**"
    ]
   },
   {
@@ -293,7 +293,7 @@
     "colab_type": "text"
    },
    "source": [
-    "#### Tensor operations: doing math in TensorFlow"
+    "#### Tensor operations: Doing math in TensorFlow"
    ]
   },
   {
@@ -327,7 +327,7 @@
     "colab_type": "text"
    },
    "source": [
-    "#### A second look at the `GradientTape` API"
+    "#### A second look at the GradientTape API"
    ]
   },
   {
@@ -336,7 +336,7 @@
     "colab_type": "text"
    },
    "source": [
-    "**Using the GradientTape**"
+    "**Using the `GradientTape`**"
    ]
   },
   {
@@ -359,7 +359,7 @@
     "colab_type": "text"
    },
    "source": [
-    "**Using the GradientTape with constant tensor inputs**"
+    "**Using `GradientTape` with constant tensor inputs**"
    ]
   },
   {
@@ -408,7 +408,7 @@
     "colab_type": "text"
    },
    "source": [
-    "#### An end-to-end example: a linear classifier in pure TensorFlow"
+    "#### An end-to-end example: A linear classifier in pure TensorFlow"
    ]
   },
   {
@@ -430,9 +430,13 @@
    "source": [
     "num_samples_per_class = 1000\n",
     "negative_samples = np.random.multivariate_normal(\n",
-    "    mean=[0, 3], cov=[[1, 0.5],[0.5, 1]], size=num_samples_per_class)\n",
+    "    mean=[0, 3],\n",
+    "    cov=[[1, 0.5],[0.5, 1]],\n",
+    "    size=num_samples_per_class)\n",
     "positive_samples = np.random.multivariate_normal(\n",
-    "    mean=[3, 0], cov=[[1, 0.5],[0.5, 1]], size=num_samples_per_class)"
+    "    mean=[3, 0],\n",
+    "    cov=[[1, 0.5],[0.5, 1]],\n",
+    "    size=num_samples_per_class)"
    ]
   },
   {
@@ -648,7 +652,7 @@
     "colab_type": "text"
    },
    "source": [
-    "## Anatomy of a neural network: understanding core Keras APIs"
+    "## Anatomy of a neural network: Understanding core Keras APIs"
    ]
   },
   {
@@ -657,7 +661,7 @@
     "colab_type": "text"
    },
    "source": [
-    "### Layers: the building blocks of deep learning"
+    "### Layers: The building blocks of deep learning"
    ]
   },
   {
@@ -666,7 +670,16 @@
     "colab_type": "text"
    },
    "source": [
-    "#### The base `Layer` class in Keras"
+    "#### The base Layer class in Keras"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "colab_type": "text"
+   },
+   "source": [
+    "**A `Dense` layer implemented as a `Layer` subclass**"
    ]
   },
   {
@@ -720,7 +733,7 @@
     "colab_type": "text"
    },
    "source": [
-    "#### Automatic shape inference: building layers on the fly"
+    "#### Automatic shape inference: Building layers on the fly"
    ]
   },
   {
@@ -782,7 +795,7 @@
     "colab_type": "text"
    },
    "source": [
-    "### The \"compile\" step: configuring the learning process"
+    "### The \"compile\" step: Configuring the learning process"
    ]
   },
   {
@@ -827,7 +840,7 @@
     "colab_type": "text"
    },
    "source": [
-    "### Understanding the `fit` method"
+    "### Understanding the fit() method"
    ]
   },
   {
@@ -836,7 +849,7 @@
     "colab_type": "text"
    },
    "source": [
-    "**Calling `fit` with NumPy data**"
+    "**Calling `fit()` with NumPy data**"
    ]
   },
   {
@@ -872,7 +885,7 @@
     "colab_type": "text"
    },
    "source": [
-    "### Monitoring loss & metrics on validation data"
+    "### Monitoring loss and metrics on validation data"
    ]
   },
   {
@@ -881,7 +894,7 @@
     "colab_type": "text"
    },
    "source": [
-    "**Using the validation data argument**"
+    "**Using the `validation_data` argument**"
    ]
   },
   {
@@ -921,7 +934,7 @@
     "colab_type": "text"
    },
    "source": [
-    "### Inference: using a model after training"
+    "### Inference: Using a model after training"
    ]
   },
   {
@@ -942,7 +955,7 @@
     "colab_type": "text"
    },
    "source": [
-    "## Chapter summary"
+    "## Summary"
    ]
   }
  ],
diff --git a/chapter04_getting-started-with-neural-networks.ipynb b/chapter04_getting-started-with-neural-networks.ipynb
index bd9ade7362..ba77a17d45 100644
--- a/chapter04_getting-started-with-neural-networks.ipynb
+++ b/chapter04_getting-started-with-neural-networks.ipynb
@@ -15,7 +15,7 @@
     "colab_type": "text"
    },
    "source": [
-    "# Getting started with neural networks: classification and regression"
+    "# Getting started with neural networks: Classification and regression"
    ]
   },
   {
@@ -24,7 +24,7 @@
     "colab_type": "text"
    },
    "source": [
-    "## Classifying movie reviews: a binary classification example"
+    "## Classifying movie reviews: A binary classification example"
    ]
   },
   {
@@ -445,7 +445,7 @@
     "colab_type": "text"
    },
    "source": [
-    "## Classifying newswires: a multiclass classification example"
+    "## Classifying newswires: A multiclass classification example"
    ]
   },
   {
@@ -994,7 +994,7 @@
     "colab_type": "text"
    },
    "source": [
-    "## Predicting house prices: a regression example"
+    "## Predicting house prices: A regression example"
    ]
   },
   {
@@ -1378,7 +1378,7 @@
     "colab_type": "text"
    },
    "source": [
-    "## Chapter summary"
+    "## Summary"
    ]
   }
  ],
diff --git a/chapter05_fundamentals-of-ml.ipynb b/chapter05_fundamentals-of-ml.ipynb
index ccf374db6b..dd61f4ead8 100644
--- a/chapter05_fundamentals-of-ml.ipynb
+++ b/chapter05_fundamentals-of-ml.ipynb
@@ -24,7 +24,7 @@
     "colab_type": "text"
    },
    "source": [
-    "## Generalization: the goal of machine learning"
+    "## Generalization: The goal of machine learning"
    ]
   },
   {
@@ -699,9 +699,9 @@
    },
    "outputs": [],
    "source": [
-    "from\u00a0keras\u00a0import\u00a0regularizers\n",
+    "from tensorflow.keras import regularizers\n",
     "regularizers.l1(0.001)\n",
-    "regularizers.l1_l2(l1=0.001,\u00a0l2=0.001)"
+    "regularizers.l1_l2(l1=0.001, l2=0.001)"
    ]
   },
   {
@@ -751,7 +751,7 @@
     "colab_type": "text"
    },
    "source": [
-    "## Chapter summary"
+    "## Summary"
    ]
   }
  ],
diff --git a/chapter07_working-with-keras.ipynb b/chapter07_working-with-keras.ipynb
index 9c979b2296..46426e00c0 100644
--- a/chapter07_working-with-keras.ipynb
+++ b/chapter07_working-with-keras.ipynb
@@ -15,7 +15,7 @@
     "colab_type": "text"
    },
    "source": [
-    "# Working with Keras: a deep dive"
+    "# Working with Keras: A deep dive"
    ]
   },
   {
@@ -51,7 +51,7 @@
     "colab_type": "text"
    },
    "source": [
-    "**The Sequential class**"
+    "**The `Sequential` class**"
    ]
   },
   {
@@ -227,7 +227,7 @@
     "colab_type": "text"
    },
    "source": [
-    "**A simple Functional model with two Dense layers**"
+    "**A simple Functional model with two `Dense` layers**"
    ]
   },
   {
@@ -403,7 +403,7 @@
     "priority_data = np.random.random(size=(num_samples, 1))\n",
     "department_data = np.random.randint(0, 2, size=(num_samples, num_departments))\n",
     "\n",
-    "model.compile(optimizer=\"adam\",\n",
+    "model.compile(optimizer=\"rmsprop\",\n",
     "              loss=[\"mean_squared_error\", \"categorical_crossentropy\"],\n",
     "              metrics=[[\"mean_absolute_error\"], [\"accuracy\"]])\n",
     "model.fit([title_data, text_body_data, tags_data],\n",
@@ -431,7 +431,7 @@
    },
    "outputs": [],
    "source": [
-    "model.compile(optimizer=\"adam\",\n",
+    "model.compile(optimizer=\"rmsprop\",\n",
     "              loss={\"priority\": \"mean_squared_error\", \"department\": \"categorical_crossentropy\"},\n",
     "              metrics={\"priority\": [\"mean_absolute_error\"], \"department\": [\"accuracy\"]})\n",
     "model.fit({\"title\": title_data, \"text_body\": text_body_data, \"tags\": tags_data},\n",
@@ -449,16 +449,7 @@
     "colab_type": "text"
    },
    "source": [
-    "#### The power of the Functional API: access to layer connectivity"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {
-    "colab_type": "text"
-   },
-   "source": [
-    "##### Plotting layer connectivity"
+    "#### The power of the Functional API: Access to layer connectivity"
    ]
   },
   {
@@ -483,15 +474,6 @@
     "keras.utils.plot_model(model, \"ticket_classifier_with_shape_info.png\", show_shapes=True)"
    ]
   },
-  {
-   "cell_type": "markdown",
-   "metadata": {
-    "colab_type": "text"
-   },
-   "source": [
-    "##### Feature extraction with a Functional model"
-   ]
-  },
   {
    "cell_type": "markdown",
    "metadata": {
@@ -576,7 +558,7 @@
     "colab_type": "text"
    },
    "source": [
-    "### Subclassing the `Model` class"
+    "### Subclassing the Model class"
    ]
   },
   {
@@ -649,16 +631,21 @@
    },
    "outputs": [],
    "source": [
-    "model.compile(optimizer=\"adam\",\n",
+    "model.compile(optimizer=\"rmsprop\",\n",
     "              loss=[\"mean_squared_error\", \"categorical_crossentropy\"],\n",
     "              metrics=[[\"mean_absolute_error\"], [\"accuracy\"]])\n",
-    "model.fit({\"title\": title_data, \"text_body\": text_body_data, \"tags\": tags_data},\n",
+    "model.fit({\"title\": title_data,\n",
+    "           \"text_body\": text_body_data,\n",
+    "           \"tags\": tags_data},\n",
     "          [priority_data, department_data],\n",
     "          epochs=1)\n",
-    "model.evaluate({\"title\": title_data, \"text_body\": text_body_data, \"tags\": tags_data},\n",
+    "model.evaluate({\"title\": title_data,\n",
+    "                \"text_body\": text_body_data,\n",
+    "                \"tags\": tags_data},\n",
     "               [priority_data, department_data])\n",
-    "priority_preds, department_preds = model.predict(\n",
-    "    {\"title\": title_data, \"text_body\": text_body_data, \"tags\": tags_data})"
+    "priority_preds, department_preds = model.predict({\"title\": title_data,\n",
+    "                                                  \"text_body\": text_body_data,\n",
+    "                                                  \"tags\": tags_data})"
    ]
   },
   {
@@ -667,7 +654,7 @@
     "colab_type": "text"
    },
    "source": [
-    "#### Beware: what subclassed models don't support"
+    "#### Beware: What subclassed models don't support"
    ]
   },
   {
@@ -758,7 +745,7 @@
     "colab_type": "text"
    },
    "source": [
-    "### Remember: use the right tool for the job"
+    "### Remember: Use the right tool for the job"
    ]
   },
   {
@@ -776,7 +763,7 @@
     "colab_type": "text"
    },
    "source": [
-    "**The standard workflow: `compile()` / `fit()` / `evaluate()` / `predict()`**"
+    "**The standard workflow: `compile()`, `fit()`, `evaluate()`, `predict()`**"
    ]
   },
   {
@@ -889,7 +876,7 @@
     "colab_type": "text"
    },
    "source": [
-    "### Using Callbacks"
+    "### Using callbacks"
    ]
   },
   {
@@ -898,7 +885,7 @@
     "colab_type": "text"
    },
    "source": [
-    "#### The `EarlyStopping` and `ModelCheckpoint` callbacks"
+    "#### The EarlyStopping and ModelCheckpoint callbacks"
    ]
   },
   {
@@ -920,8 +907,8 @@
    "source": [
     "callbacks_list = [\n",
     "    keras.callbacks.EarlyStopping(\n",
-    "        monitor=\"accuracy\",\n",
-    "        patience=1,\n",
+    "        monitor=\"val_accuracy\",\n",
+    "        patience=2,\n",
     "    ),\n",
     "    keras.callbacks.ModelCheckpoint(\n",
     "        filepath=\"checkpoint_path.keras\",\n",
@@ -1263,7 +1250,7 @@
     "colab_type": "text"
    },
    "source": [
-    "### Make it fast with `tf.function`"
+    "### Make it fast with tf.function"
    ]
   },
   {
@@ -1272,7 +1259,7 @@
     "colab_type": "text"
    },
    "source": [
-    "**Adding a `tf.function` decorator to our evaluation step function**"
+    "**Adding a `tf.function` decorator to our evaluation-step function**"
    ]
   },
   {
@@ -1313,7 +1300,7 @@
     "colab_type": "text"
    },
    "source": [
-    "### Leveraging `fit()` with a custom training loop"
+    "### Leveraging fit() with a custom training loop"
    ]
   },
   {
@@ -1417,7 +1404,7 @@
     "colab_type": "text"
    },
    "source": [
-    "## Chapter summary"
+    "## Summary"
    ]
   }
  ],
diff --git a/chapter08_intro-to-dl-for-computer-vision.ipynb b/chapter08_intro-to-dl-for-computer-vision.ipynb
index aaa2f47005..60072bce8a 100644
--- a/chapter08_intro-to-dl-for-computer-vision.ipynb
+++ b/chapter08_intro-to-dl-for-computer-vision.ipynb
@@ -170,7 +170,7 @@
     "colab_type": "text"
    },
    "source": [
-    "**An incorrectly-structured convnet missing its max pooling layers**"
+    "**An incorrectly structured convnet missing its max-pooling layers**"
    ]
   },
   {
@@ -317,7 +317,7 @@
     "colab_type": "text"
    },
    "source": [
-    "### Building your model"
+    "### Building the model"
    ]
   },
   {
@@ -404,7 +404,7 @@
     "colab_type": "text"
    },
    "source": [
-    "**Using `image_dataset_from_directory` to read images from directories**"
+    "**Using `image_dataset_from_directory` to read images**"
    ]
   },
   {
@@ -431,15 +431,6 @@
     "    batch_size=32)"
    ]
   },
-  {
-   "cell_type": "markdown",
-   "metadata": {
-    "colab_type": "text"
-   },
-   "source": [
-    "**Instantiating a Dataset from a NumPy array**"
-   ]
-  },
   {
    "cell_type": "code",
    "execution_count": 0,
@@ -454,15 +445,6 @@
     "dataset = tf.data.Dataset.from_tensor_slices(random_numbers)"
    ]
   },
-  {
-   "cell_type": "markdown",
-   "metadata": {
-    "colab_type": "text"
-   },
-   "source": [
-    "**Iterating on a dataset**"
-   ]
-  },
   {
    "cell_type": "code",
    "execution_count": 0,
@@ -477,15 +459,6 @@
     "        break"
    ]
   },
-  {
-   "cell_type": "markdown",
-   "metadata": {
-    "colab_type": "text"
-   },
-   "source": [
-    "**Batching a dataset**"
-   ]
-  },
   {
    "cell_type": "code",
    "execution_count": 0,
@@ -501,15 +474,6 @@
     "        break"
    ]
   },
-  {
-   "cell_type": "markdown",
-   "metadata": {
-    "colab_type": "text"
-   },
-   "source": [
-    "**Applying a transformation to Dataset elements using `map()`**"
-   ]
-  },
   {
    "cell_type": "code",
    "execution_count": 0,
@@ -531,7 +495,7 @@
     "colab_type": "text"
    },
    "source": [
-    "**Displaying the shapes of the data and labels yielded by the Dataset**"
+    "**Displaying the shapes of the data and labels yielded by the `Dataset`**"
    ]
   },
   {
@@ -554,7 +518,7 @@
     "colab_type": "text"
    },
    "source": [
-    "**Fitting the model using a Dataset**"
+    "**Fitting the model using a `Dataset`**"
    ]
   },
   {
@@ -984,7 +948,7 @@
     "colab_type": "text"
    },
    "source": [
-    "**Instantiating and freeze the VGG16 convolutional base**"
+    "**Instantiating and freezing the VGG16 convolutional base**"
    ]
   },
   {
@@ -1042,7 +1006,7 @@
     "colab_type": "text"
    },
    "source": [
-    "**Adding data augmentation and a densely-connected classifier to the frozen convolutional base**"
+    "**Adding a data augmentation stage and a classifier to the convolutional base**"
    ]
   },
   {
@@ -1145,7 +1109,7 @@
     "colab_type": "text"
    },
    "source": [
-    "**Freezing all layers until the 4th from the last**"
+    "**Freezing all layers until the fourth from the last**"
    ]
   },
   {
@@ -1214,7 +1178,7 @@
     "colab_type": "text"
    },
    "source": [
-    "## Chapter summary"
+    "## Summary"
    ]
   }
  ],
diff --git a/chapter09_part02_modern-convnet-architecture-patterns.ipynb b/chapter09_part02_modern-convnet-architecture-patterns.ipynb
index b8136b0764..941946b2e2 100644
--- a/chapter09_part02_modern-convnet-architecture-patterns.ipynb
+++ b/chapter09_part02_modern-convnet-architecture-patterns.ipynb
@@ -42,7 +42,7 @@
     "colab_type": "text"
    },
    "source": [
-    "**Case where the target block changes the number of output filters**"
+    "**Residual block where the number of filters changes**"
    ]
   },
   {
@@ -70,7 +70,7 @@
     "colab_type": "text"
    },
    "source": [
-    "**Case where the target block includes a max pooling layer**"
+    "**Case where target block includes a max pooling layer**"
    ]
   },
   {
@@ -147,7 +147,7 @@
     "colab_type": "text"
    },
    "source": [
-    "### Putting it together: a mini Xception-like model"
+    "### Putting it together: A mini Xception-like model"
    ]
   },
   {
diff --git a/chapter09_part03_interpreting-what-convnets-learn.ipynb b/chapter09_part03_interpreting-what-convnets-learn.ipynb
index 9f9c4aba11..0767d47e71 100644
--- a/chapter09_part03_interpreting-what-convnets-learn.ipynb
+++ b/chapter09_part03_interpreting-what-convnets-learn.ipynb
@@ -297,7 +297,7 @@
     "colab_type": "text"
    },
    "source": [
-    "**Creating a \"feature extractor\" model that returns the output of a specific layer**"
+    "**Creating a feature extractor model**"
    ]
   },
   {
@@ -612,7 +612,7 @@
     "colab_type": "text"
    },
    "source": [
-    "**Setting up a model that goes from the last convolutional output to the final predictions**"
+    "**Reapplying the classifier on top of the last convolutional output**"
    ]
   },
   {
@@ -636,7 +636,7 @@
     "colab_type": "text"
    },
    "source": [
-    "**Retrieving the gradients of the top predicted class with regard to the last convolutional output**"
+    "**Retrieving the gradients of the top predicted class**"
    ]
   },
   {
@@ -665,7 +665,7 @@
     "colab_type": "text"
    },
    "source": [
-    "**Gradient pooling and channel importance weighting**"
+    "**Gradient pooling and channel-importance weighting**"
    ]
   },
   {
@@ -711,7 +711,7 @@
     "colab_type": "text"
    },
    "source": [
-    "**Superimposing the heatmap with the original picture**"
+    "**Superimposing the heatmap on the original picture**"
    ]
   },
   {
@@ -750,7 +750,7 @@
     "colab_type": "text"
    },
    "source": [
-    "## Chapter summary"
+    "## Summary"
    ]
   }
  ],
diff --git a/chapter10_dl-for-timeseries.ipynb b/chapter10_dl-for-timeseries.ipynb
index 24ecd832ac..48735a24cf 100644
--- a/chapter10_dl-for-timeseries.ipynb
+++ b/chapter10_dl-for-timeseries.ipynb
@@ -33,7 +33,7 @@
     "colab_type": "text"
    },
    "source": [
-    "## A temperature forecasting example"
+    "## A temperature-forecasting example"
    ]
   },
   {
@@ -151,7 +151,7 @@
     "colab_type": "text"
    },
    "source": [
-    "**Computing the number of samples we'll use for each data split.**"
+    "**Computing the number of samples we'll use for each data split**"
    ]
   },
   {
@@ -231,7 +231,7 @@
     "colab_type": "text"
    },
    "source": [
-    "**Instantiating Datasets for training, validation, and testing.**"
+    "**Instantiating datasets for training, validation, and testing**"
    ]
   },
   {
@@ -283,7 +283,7 @@
     "colab_type": "text"
    },
    "source": [
-    "**Inspecting the output of one of our Datasets.**"
+    "**Inspecting the output of one of our datasets**"
    ]
   },
   {
@@ -345,7 +345,7 @@
     "colab_type": "text"
    },
    "source": [
-    "### Let's try a basic machine learning model"
+    "### Let's try a basic machine-learning model"
    ]
   },
   {
@@ -500,7 +500,7 @@
     "                    callbacks=callbacks)\n",
     "\n",
     "model = keras.models.load_model(\"jena_lstm.keras\")\n",
-    "print(\"Test MAE: {model.evaluate(test_dataset)[1]:.2f}\")"
+    "print(f\"Test MAE: {model.evaluate(test_dataset)[1]:.2f}\")"
    ]
   },
   {
@@ -561,7 +561,7 @@
     "colab_type": "text"
    },
    "source": [
-    "**A RNN layer that can process sequences of any length**"
+    "**An RNN layer that can process sequences of any length**"
    ]
   },
   {
@@ -583,7 +583,7 @@
     "colab_type": "text"
    },
    "source": [
-    "**A RNN layer that returns only its last output step**"
+    "**An RNN layer that returns only its last output step**"
    ]
   },
   {
@@ -607,7 +607,7 @@
     "colab_type": "text"
    },
    "source": [
-    "**A RNN layer that returns its full output sequence**"
+    "**An RNN layer that returns its full output sequence**"
    ]
   },
   {
@@ -801,7 +801,7 @@
     "colab_type": "text"
    },
    "source": [
-    "### *_Going even further_*"
+    "### Going even further"
    ]
   },
   {
@@ -810,7 +810,7 @@
     "colab_type": "text"
    },
    "source": [
-    "## Chapter summary"
+    "## Summary"
    ]
   }
  ],
diff --git a/chapter11_part01_introduction.ipynb b/chapter11_part01_introduction.ipynb
index 1c9708d04f..3ef20b7618 100644
--- a/chapter11_part01_introduction.ipynb
+++ b/chapter11_part01_introduction.ipynb
@@ -24,7 +24,7 @@
     "colab_type": "text"
    },
    "source": [
-    "## Natural Language Processing: the bird's eye view"
+    "## Natural-language processing: The bird's eye view"
    ]
   },
   {
@@ -69,7 +69,7 @@
     "colab_type": "text"
    },
    "source": [
-    "### Using the `TextVectorization` layer"
+    "### Using the TextVectorization layer"
    ]
   },
   {
@@ -255,7 +255,7 @@
     "colab_type": "text"
    },
    "source": [
-    "## Two approaches for representing groups of words: sets and sequences"
+    "## Two approaches for representing groups of words: Sets and sequences"
    ]
   },
   {
@@ -380,7 +380,7 @@
     "colab_type": "text"
    },
    "source": [
-    "### Processing words as a set: the bag-of-words approach"
+    "### Processing words as a set: The bag-of-words approach"
    ]
   },
   {
@@ -411,14 +411,20 @@
    "source": [
     "text_vectorization = TextVectorization(\n",
     "    max_tokens=20000,\n",
-    "    output_mode=\"binary\",\n",
+    "    output_mode=\"multi_hot\",\n",
     ")\n",
     "text_only_train_ds = train_ds.map(lambda x, y: x)\n",
     "text_vectorization.adapt(text_only_train_ds)\n",
     "\n",
-    "binary_1gram_train_ds = train_ds.map(lambda x, y: (text_vectorization(x), y))\n",
-    "binary_1gram_val_ds = val_ds.map(lambda x, y: (text_vectorization(x), y))\n",
-    "binary_1gram_test_ds = test_ds.map(lambda x, y: (text_vectorization(x), y))"
+    "binary_1gram_train_ds = train_ds.map(\n",
+    "    lambda x, y: (text_vectorization(x), y),\n",
+    "    num_parallel_calls=4)\n",
+    "binary_1gram_val_ds = val_ds.map(\n",
+    "    lambda x, y: (text_vectorization(x), y),\n",
+    "    num_parallel_calls=4)\n",
+    "binary_1gram_test_ds = test_ds.map(\n",
+    "    lambda x, y: (text_vectorization(x), y),\n",
+    "    num_parallel_calls=4)"
    ]
   },
   {
@@ -540,7 +546,7 @@
     "text_vectorization = TextVectorization(\n",
     "    ngrams=2,\n",
     "    max_tokens=20000,\n",
-    "    output_mode=\"binary\",\n",
+    "    output_mode=\"multi_hot\",\n",
     ")"
    ]
   },
@@ -562,9 +568,15 @@
    "outputs": [],
    "source": [
     "text_vectorization.adapt(text_only_train_ds)\n",
-    "binary_2gram_train_ds = train_ds.map(lambda x, y: (text_vectorization(x), y))\n",
-    "binary_2gram_val_ds = val_ds.map(lambda x, y: (text_vectorization(x), y))\n",
-    "binary_2gram_test_ds = test_ds.map(lambda x, y: (text_vectorization(x), y))\n",
+    "binary_2gram_train_ds = train_ds.map(\n",
+    "    lambda x, y: (text_vectorization(x), y),\n",
+    "    num_parallel_calls=4)\n",
+    "binary_2gram_val_ds = val_ds.map(\n",
+    "    lambda x, y: (text_vectorization(x), y),\n",
+    "    num_parallel_calls=4)\n",
+    "binary_2gram_test_ds = test_ds.map(\n",
+    "    lambda x, y: (text_vectorization(x), y),\n",
+    "    num_parallel_calls=4)\n",
     "\n",
     "model = get_model()\n",
     "model.summary()\n",
@@ -619,7 +631,7 @@
     "colab_type": "text"
    },
    "source": [
-    "**Configuring the `TextVectorization` layer to return TF-IDF-weighted outputs**"
+    "**Configuring `TextVectorization` to return TF-IDF-weighted outputs**"
    ]
   },
   {
@@ -656,9 +668,15 @@
    "source": [
     "text_vectorization.adapt(text_only_train_ds)\n",
     "\n",
-    "tfidf_2gram_train_ds = train_ds.map(lambda x, y: (text_vectorization(x), y))\n",
-    "tfidf_2gram_val_ds = val_ds.map(lambda x, y: (text_vectorization(x), y))\n",
-    "tfidf_2gram_test_ds = test_ds.map(lambda x, y: (text_vectorization(x), y))\n",
+    "tfidf_2gram_train_ds = train_ds.map(\n",
+    "    lambda x, y: (text_vectorization(x), y),\n",
+    "    num_parallel_calls=4)\n",
+    "tfidf_2gram_val_ds = val_ds.map(\n",
+    "    lambda x, y: (text_vectorization(x), y),\n",
+    "    num_parallel_calls=4)\n",
+    "tfidf_2gram_test_ds = test_ds.map(\n",
+    "    lambda x, y: (text_vectorization(x), y),\n",
+    "    num_parallel_calls=4)\n",
     "\n",
     "model = get_model()\n",
     "model.summary()\n",
diff --git a/chapter11_part02_sequence-models.ipynb b/chapter11_part02_sequence-models.ipynb
index 7bc8912ec9..ee1fac0fbd 100644
--- a/chapter11_part02_sequence-models.ipynb
+++ b/chapter11_part02_sequence-models.ipynb
@@ -15,7 +15,7 @@
     "colab_type": "text"
    },
    "source": [
-    "### Processing words as a sequence: the Sequence Model approach"
+    "### Processing words as a sequence: The sequence model approach"
    ]
   },
   {
@@ -122,9 +122,15 @@
     ")\n",
     "text_vectorization.adapt(text_only_train_ds)\n",
     "\n",
-    "int_train_ds = train_ds.map(lambda x, y: (text_vectorization(x), y))\n",
-    "int_val_ds = val_ds.map(lambda x, y: (text_vectorization(x), y))\n",
-    "int_test_ds = test_ds.map(lambda x, y: (text_vectorization(x), y))"
+    "int_train_ds = train_ds.map(\n",
+    "    lambda x, y: (text_vectorization(x), y)),\n",
+    "    num_parallel_calls=4)\n",
+    "int_val_ds = val_ds.map(\n",
+    "    lambda x, y: (text_vectorization(x), y),\n",
+    "    num_parallel_calls=4)\n",
+    "int_test_ds = test_ds.map(\n",
+    "    lambda x, y: (text_vectorization(x), y),\n",
+    "    num_parallel_calls=4)"
    ]
   },
   {
@@ -133,7 +139,7 @@
     "colab_type": "text"
    },
    "source": [
-    "**A sequence model built on top of one-hot encoded vector sequences**"
+    "**A sequence model built on one-hot encoded vector sequences**"
    ]
   },
   {
@@ -198,7 +204,7 @@
     "colab_type": "text"
    },
    "source": [
-    "##### Learning word embeddings with the `Embedding` layer"
+    "#### Learning word embeddings with the Embedding layer"
    ]
   },
   {
@@ -227,7 +233,7 @@
     "colab_type": "text"
    },
    "source": [
-    "**Model that uses an Embedding layer trained from scratch**"
+    "**Model that uses an `Embedding` layer trained from scratch**"
    ]
   },
   {
@@ -264,7 +270,7 @@
     "colab_type": "text"
    },
    "source": [
-    "###### Understanding padding & masking"
+    "#### Understanding padding and masking"
    ]
   },
   {
@@ -273,7 +279,7 @@
     "colab_type": "text"
    },
    "source": [
-    "**Model that uses an Embedding layer trained from scratch, with masking enabled**"
+    "**Using an `Embedding` layer with masking enabled**"
    ]
   },
   {
@@ -311,16 +317,7 @@
     "colab_type": "text"
    },
    "source": [
-    "##### Using pretrained word embeddings"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {
-    "colab_type": "text"
-   },
-   "source": [
-    "###### Downloading the GloVe word embeddings"
+    "#### Using pretrained word embeddings"
    ]
   },
   {
@@ -365,15 +362,6 @@
     "print(f\"Found {len(embeddings_index)} word vectors.\")"
    ]
   },
-  {
-   "cell_type": "markdown",
-   "metadata": {
-    "colab_type": "text"
-   },
-   "source": [
-    "###### Loading the GloVe embeddings in the model"
-   ]
-  },
   {
    "cell_type": "markdown",
    "metadata": {
@@ -421,15 +409,6 @@
     ")"
    ]
   },
-  {
-   "cell_type": "markdown",
-   "metadata": {
-    "colab_type": "text"
-   },
-   "source": [
-    "###### Training a simple bidirectional LSTM on top of the GloVe embeddings"
-   ]
-  },
   {
    "cell_type": "markdown",
    "metadata": {
diff --git a/chapter11_part03_transformer.ipynb b/chapter11_part03_transformer.ipynb
index 397e92e90a..0cab099487 100644
--- a/chapter11_part03_transformer.ipynb
+++ b/chapter11_part03_transformer.ipynb
@@ -42,7 +42,7 @@
     "colab_type": "text"
    },
    "source": [
-    "### Multi-Head attention"
+    "### Multi-head attention"
    ]
   },
   {
@@ -149,9 +149,15 @@
     ")\n",
     "text_vectorization.adapt(text_only_train_ds)\n",
     "\n",
-    "int_train_ds = train_ds.map(lambda x, y: (text_vectorization(x), y))\n",
-    "int_val_ds = val_ds.map(lambda x, y: (text_vectorization(x), y))\n",
-    "int_test_ds = test_ds.map(lambda x, y: (text_vectorization(x), y))"
+    "int_train_ds = train_ds.map(\n",
+    "    lambda x, y: (text_vectorization(x), y),\n",
+    "    num_parallel_calls=4)\n",
+    "int_val_ds = val_ds.map(\n",
+    "    lambda x, y: (text_vectorization(x), y),\n",
+    "    num_parallel_calls=4)\n",
+    "int_test_ds = test_ds.map(\n",
+    "    lambda x, y: (text_vectorization(x), y),\n",
+    "    num_parallel_calls=4)"
    ]
   },
   {
@@ -160,7 +166,7 @@
     "colab_type": "text"
    },
    "source": [
-    "**Transformer encoder implemented as a subclassed Layer**"
+    "**Transformer encoder implemented as a subclassed `Layer`**"
    ]
   },
   {
@@ -215,7 +221,7 @@
     "colab_type": "text"
    },
    "source": [
-    "**Text classification model that combines the Transformer encoder and a pooling layer**"
+    "**Using the Transformer encoder for text classification**"
    ]
   },
   {
@@ -278,7 +284,7 @@
     "colab_type": "text"
    },
    "source": [
-    "#### Using positional encoding to reinject order information"
+    "#### Using positional encoding to re-inject order information"
    ]
   },
   {
@@ -335,7 +341,7 @@
     "colab_type": "text"
    },
    "source": [
-    "#### Putting it all together: a text-classification Transformer"
+    "#### Putting it all together: A text-classification Transformer"
    ]
   },
   {
@@ -344,7 +350,7 @@
     "colab_type": "text"
    },
    "source": [
-    "**Text classification model that combines positional embedding, the Transformer encoder, and a pooling layer**"
+    "**Combining the Transformer encoder with positional embedding**"
    ]
   },
   {
diff --git a/chapter11_part04_sequence-to-sequence-learning.ipynb b/chapter11_part04_sequence-to-sequence-learning.ipynb
index 388e64dc25..a08929dedb 100644
--- a/chapter11_part04_sequence-to-sequence-learning.ipynb
+++ b/chapter11_part04_sequence-to-sequence-learning.ipynb
@@ -15,7 +15,7 @@
     "colab_type": "text"
    },
    "source": [
-    "## Beyond text classification: sequence-to-sequence learning"
+    "## Beyond text classification: Sequence-to-sequence learning"
    ]
   },
   {
@@ -142,7 +142,7 @@
     "colab_type": "text"
    },
    "source": [
-    "**Preparing training and validation datasets for the translation task**"
+    "**Preparing datasets for the translation task**"
    ]
   },
   {
@@ -169,7 +169,7 @@
     "    spa_texts = list(spa_texts)\n",
     "    dataset = tf.data.Dataset.from_tensor_slices((eng_texts, spa_texts))\n",
     "    dataset = dataset.batch(batch_size)\n",
-    "    dataset = dataset.map(format_dataset)\n",
+    "    dataset = dataset.map(format_dataset, num_parallel_calls=4)\n",
     "    return dataset.shuffle(2048).prefetch(16).cache()\n",
     "\n",
     "train_ds = make_dataset(train_pairs)\n",
@@ -346,7 +346,7 @@
     "colab_type": "text"
    },
    "source": [
-    "**The TransformerDecoder**"
+    "**The `TransformerDecoder`**"
    ]
   },
   {
@@ -427,7 +427,7 @@
     "colab_type": "text"
    },
    "source": [
-    "#### Putting it all together: a Transformer for machine translation"
+    "#### Putting it all together: A Transformer for machine translation"
    ]
   },
   {
@@ -586,7 +586,7 @@
     "colab_type": "text"
    },
    "source": [
-    "## Chapter summary"
+    "## Summary"
    ]
   }
  ],
diff --git a/chapter12_part01_text-generation.ipynb b/chapter12_part01_text-generation.ipynb
index 6fa2f175f7..1c43438d3b 100644
--- a/chapter12_part01_text-generation.ipynb
+++ b/chapter12_part01_text-generation.ipynb
@@ -123,7 +123,7 @@
     "colab_type": "text"
    },
    "source": [
-    "**Creating a Dataset that yields the content of a set of text files (one file = one sample)**"
+    "**Creating a dataset from text files (one file = one sample)**"
    ]
   },
   {
@@ -147,7 +147,7 @@
     "colab_type": "text"
    },
    "source": [
-    "**Preparing a TextVectorization layer**"
+    "**Preparing a `TextVectorization` layer**"
    ]
   },
   {
@@ -193,8 +193,7 @@
     "    y = vectorized_sequences[:, 1:]\n",
     "    return x, y\n",
     "\n",
-    "lm_dataset = dataset.map(prepare_lm_dataset)\n",
-    "lm_dataset = lm_dataset.prefetch(8)"
+    "lm_dataset = dataset.map(prepare_lm_dataset, num_parallel_calls=4)"
    ]
   },
   {
@@ -357,7 +356,7 @@
     "colab_type": "text"
    },
    "source": [
-    "**The text generation callback**"
+    "**The text-generation callback**"
    ]
   },
   {
diff --git a/chapter12_part02_deep-dream.ipynb b/chapter12_part02_deep-dream.ipynb
index 4827f1587e..7e01d0fbee 100644
--- a/chapter12_part02_deep-dream.ipynb
+++ b/chapter12_part02_deep-dream.ipynb
@@ -27,6 +27,15 @@
     "### Implementing DeepDream in Keras"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "colab_type": "text"
+   },
+   "source": [
+    "**Fetching the test image**"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": 0,
@@ -45,6 +54,15 @@
     "plt.imshow(keras.utils.load_img(base_image_path))"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "colab_type": "text"
+   },
+   "source": [
+    "**Instantiating a pretrained `InceptionV3` model**"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": 0,
@@ -57,6 +75,15 @@
     "model = inception_v3.InceptionV3(weights=\"imagenet\", include_top=False)"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "colab_type": "text"
+   },
+   "source": [
+    "**Configuring the contribution of each layer to the DeepDream loss**"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": 0,
@@ -80,6 +107,15 @@
     "feature_extractor = keras.Model(inputs=model.inputs, outputs=outputs_dict)"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "colab_type": "text"
+   },
+   "source": [
+    "**The DeepDream loss**"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": 0,
@@ -98,6 +134,15 @@
     "    return loss"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "colab_type": "text"
+   },
+   "source": [
+    "**The DeepDream gradient ascent process**"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": 0,
@@ -143,6 +188,15 @@
     "max_loss = 15."
    ]
   },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "colab_type": "text"
+   },
+   "source": [
+    "**Image processing utilities**"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": 0,
@@ -169,6 +223,15 @@
     "    return img"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "colab_type": "text"
+   },
+   "source": [
+    "**Running gradient ascent over multiple successive \"octaves\"**"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": 0,
diff --git a/chapter12_part03_neural-style-transfer.ipynb b/chapter12_part03_neural-style-transfer.ipynb
index d5ebcb0660..42fd13ef84 100644
--- a/chapter12_part03_neural-style-transfer.ipynb
+++ b/chapter12_part03_neural-style-transfer.ipynb
@@ -117,7 +117,7 @@
     "colab_type": "text"
    },
    "source": [
-    "**Loading the pretrained VGG19 network and using it to define a feature extractor**"
+    "**Using a pretrained VGG19 model to create a feature extractor**"
    ]
   },
   {
diff --git a/chapter12_part04_variational-autoencoders.ipynb b/chapter12_part04_variational-autoencoders.ipynb
index 9f44f4bde9..fd6ae9c13a 100644
--- a/chapter12_part04_variational-autoencoders.ipynb
+++ b/chapter12_part04_variational-autoencoders.ipynb
@@ -254,7 +254,7 @@
     "colab_type": "text"
    },
    "source": [
-    "**Sampling a grid of points from the 2D latent space and decoding them to images**"
+    "**Sampling a grid of images from the 2D latent space**"
    ]
   },
   {
diff --git a/chapter12_part05_gans.ipynb b/chapter12_part05_gans.ipynb
index 1e5574bf64..993542fc5b 100644
--- a/chapter12_part05_gans.ipynb
+++ b/chapter12_part05_gans.ipynb
@@ -73,7 +73,7 @@
     "colab_type": "text"
    },
    "source": [
-    "**Creating a Dataset from a directory of images**"
+    "**Creating a dataset from a directory of images**"
    ]
   },
   {
@@ -264,7 +264,7 @@
     "colab_type": "text"
    },
    "source": [
-    "**The GAN Model**"
+    "**The GAN `Model`**"
    ]
   },
   {
@@ -297,11 +297,13 @@
     "\n",
     "    def train_step(self, real_images):\n",
     "        batch_size = tf.shape(real_images)[0]\n",
-    "        random_latent_vectors = tf.random.normal(shape=(batch_size, self.latent_dim))\n",
+    "        random_latent_vectors = tf.random.normal(\n",
+    "            shape=(batch_size, self.latent_dim))\n",
     "        generated_images = self.generator(random_latent_vectors)\n",
     "        combined_images = tf.concat([generated_images, real_images], axis=0)\n",
     "        labels = tf.concat(\n",
-    "            [tf.ones((batch_size, 1)), tf.zeros((batch_size, 1))], axis=0\n",
+    "            [tf.ones((batch_size, 1)), tf.zeros((batch_size, 1))],\n",
+    "            axis=0\n",
     "        )\n",
     "        labels += 0.05 * tf.random.uniform(tf.shape(labels))\n",
     "\n",
@@ -314,19 +316,22 @@
     "        )\n",
     "\n",
     "        random_latent_vectors = tf.random.normal(\n",
-    "          shape=(batch_size, self.latent_dim))\n",
+    "            shape=(batch_size, self.latent_dim))\n",
     "\n",
     "        misleading_labels = tf.zeros((batch_size, 1))\n",
     "\n",
     "        with tf.GradientTape() as tape:\n",
-    "            predictions = self.discriminator(self.generator(random_latent_vectors))\n",
+    "            predictions = self.discriminator(\n",
+    "                self.generator(random_latent_vectors))\n",
     "            g_loss = self.loss_fn(misleading_labels, predictions)\n",
     "        grads = tape.gradient(g_loss, self.generator.trainable_weights)\n",
-    "        self.g_optimizer.apply_gradients(zip(grads, self.generator.trainable_weights))\n",
+    "        self.g_optimizer.apply_gradients(\n",
+    "            zip(grads, self.generator.trainable_weights))\n",
     "\n",
     "        self.d_loss_metric.update_state(d_loss)\n",
     "        self.g_loss_metric.update_state(g_loss)\n",
-    "        return {\"d_loss\": self.d_loss_metric.result(), \"g_loss\": self.g_loss_metric.result()}"
+    "        return {\"d_loss\": self.d_loss_metric.result(),\n",
+    "                \"g_loss\": self.g_loss_metric.result()}"
    ]
   },
   {
@@ -335,7 +340,7 @@
     "colab_type": "text"
    },
    "source": [
-    "**A callback to sample generated images during training**"
+    "**A callback that samples generated images during training**"
    ]
   },
   {
@@ -407,7 +412,7 @@
     "colab_type": "text"
    },
    "source": [
-    "## Chapter summary"
+    "## Summary"
    ]
   }
  ],
diff --git a/chapter13_best-practices-for-the-real-world.ipynb b/chapter13_best-practices-for-the-real-world.ipynb
index 8291a2e4bc..68736349e6 100644
--- a/chapter13_best-practices-for-the-real-world.ipynb
+++ b/chapter13_best-practices-for-the-real-world.ipynb
@@ -24,7 +24,7 @@
     "colab_type": "text"
    },
    "source": [
-    "## Getting the most our of your models"
+    "## Getting the most out of your models"
    ]
   },
   {
@@ -96,7 +96,7 @@
     "colab_type": "text"
    },
    "source": [
-    "**A KerasTuner HyperModel**"
+    "**A KerasTuner `HyperModel`**"
    ]
   },
   {
@@ -300,7 +300,7 @@
     "colab_type": "text"
    },
    "source": [
-    "## Scaling up model training"
+    "## Scaling-up model training"
    ]
   },
   {
@@ -309,7 +309,7 @@
     "colab_type": "text"
    },
    "source": [
-    "### Speeding up training on GPU with Mixed Precision"
+    "### Speeding up training on GPU with mixed precision"
    ]
   },
   {
@@ -430,7 +430,7 @@
     "colab_type": "text"
    },
    "source": [
-    "## Chapter summary"
+    "## Summary"
    ]
   }
  ],
diff --git a/chapter14_conclusions.ipynb b/chapter14_conclusions.ipynb
index d92e0b5c52..e8ce1e0b57 100644
--- a/chapter14_conclusions.ipynb
+++ b/chapter14_conclusions.ipynb
@@ -87,7 +87,7 @@
     "colab_type": "text"
    },
    "source": [
-    "#### Densely-connected networks"
+    "#### Densely connected networks"
    ]
   },
   {
@@ -344,7 +344,7 @@
     "colab_type": "text"
    },
    "source": [
-    "## Setting the course towards greater generality in AI"
+    "## Setting the course toward greater generality in AI"
    ]
   },
   {
@@ -353,7 +353,7 @@
     "colab_type": "text"
    },
    "source": [
-    "### On the importance of setting the right objective: the shortcut rule"
+    "### On the importance of setting the right objective: The shortcut rule"
    ]
   },
   {
@@ -371,7 +371,7 @@
     "colab_type": "text"
    },
    "source": [
-    "## Implementing intelligence: the missing ingredients"
+    "## Implementing intelligence: The missing ingredients"
    ]
   },
   {
@@ -461,7 +461,7 @@
     "colab_type": "text"
    },
    "source": [
-    "#### Integrating deep learning modules and algorithmic modules into hybrid systems"
+    "#### Integrating deep-learning modules and algorithmic modules into hybrid systems"
    ]
   },
   {