Chapter 1, *Introduction to Deep Learning in Go*, introduces the history and applications of deep learning. This chapter also gives an overview of ML with Go.

Chapter 2, *What is a Neural Network and How Do I Train One?*, covers how to build a simple neural network and how to inspect a graph, as well as many of the commonly used activation functions. This chapter also discusses some of the different options for gradient descent algorithms and optimizations for your neural network.

Chapter 3, *Beyond Basic Neural Networks – Autoencoders and RBMs*, shows how to build a simple multilayer neural network and an autoencoder. This chapter also explores the design and implementation of a probabilistic graphical model, an RBM, used in an unsupervised manner to create a recommendation engine for films.

Chapter 4, *CUDA – GPU-Accelerated Training*, looks at the hardware side of deep learning and also at exactly how CPUs and GPUs serve our computational needs.

Chapter 5, *Next Word Prediction with Recurrent Neural Networks*, goes into what a basic RNN is and how to train one. You will also get a clear idea of the RNN architecture, including GRU/LSTM networks.

Chapter 6, *Object Recognition with Convolutional Neural Networks*, shows you how to build a CNN and how to tune some of the hyperparameters (such as the number of epochs and batch sizes) in order to get the desired result and get it running smoothly on different computers.

Chapter 7, *Maze Solving with Deep Q-Networks*, gives an introduction to reinforcement learning and Q-learning and how to build a DQN and solve a maze.

Chapter 8, *Generative Models with Variational Autoencoders, shows *how to build a VAE and looks at the advantages of a VAE over a standard autoencoder. This chapter also shows how to understand the effect of varying latent space dimensions on a network.

Chapter 9, *Building a Deep Learning Pipeline*, looks at what data pipelines are and why we use Pachyderm to build or manage them.

Chapter 10, *Scaling Deployment*, looks at a number of the technologies that sit underneath Pachyderm, including Docker and Kubernetes, and also examines how we can deploy stacks to cloud infrastructure using these tools .