Chapter 1, Introducing the Google Cloud Platform, explores different services that may be useful to build a machine learning pipeline based on GCP.
Chapter 2, Google Compute Engine, helps you to create and fully manage your VM via both the online console and command-line tools, as well as how to implement a data science workflow and a Jupyter Notebook workspace.
Chapter 3, Google Cloud Storage, shows how to upload data and manage it using the services provided by the Google Cloud Platform.
Chapter 4, Querying Your Data with BigQuery, shows you how to query data from Google Storage and visualize it with Google Data Studio.
Chapter 5, Transforming Your Data, presents Dataprep, a service useful for preprocessing data, extracting features, and cleaning up records. We also look at Dataflow, a service used to implement streaming and batch processing.
Chapter 6, Essential Machine Learning, starts our journey into machine learning and deep learning; we learn when to apply each one.
Chapter 7, Google Machine Learning APIs, teaches us how to use Google Cloud machine learning APIs for image analysis, text and speech processing, translation, and video inference.
Chapter 8, Creating ML Applications with Firebase, shows how to integrate different GCP services to build a seamless machine-learning-based application, mobile or web-based.
Chapter 9, Neural Networks with TensorFlow and Keras, gives a good understanding of the structure and key elements of a feedforward network, how to architecture one, and how to tinker and experiment with different parameters.
Chapter 10, Evaluating Results with TensorBoard, shows how the choice of different parameters and functions impacts the performance of the model.
Chapter 11, Optimizing the Model through Hyperparameter Tuning, teaches us how to use hypertuning in TensorFlow application code and interpret the results to select the best performing model.
Chapter 12, Preventing Overfitting with Regularization, shows how to identify overfitting and make our models more robust to previously unseen data by setting the right parameters and defining the proper architectures.
Chapter 13, Beyond Feedforward Networks – CNN and RNNs, teaches which type of neural network to apply to different problems, and how to define and implement them on GCP.
Chapter 14, Time Series with LSTMs, shows how to create LSTMs and apply them to time series predictions. We will also understand when LSTMs outperform more standard approaches.
Chapter 15, Reinforcement Learning, introduces the power of reinforcement learning and shows how to implement a simple use case on GCP.
Chapter 16, Generative Neural Networks, teaches us how to extract the content generated within the neural net with different types of content—text, images, and sounds.
Chapter 17, Chatbots, shows how to train a contextual chatbot while implementing it in a real mobile application.
