Chapter 1, Getting Started, introduces different packages that are available for building deep learning models, such as TensorFlow, MXNet, and H2O. and how to set them up to be utilized later in the book.

Chapter 2, Deep Learning with R, introduces the basics of neural network and deep learning. This chapter covers multiple recipes for building a neural network models using multiple toolboxes in R.

Chapter 3, Convolution Neural Network, covers recipes on Convolution Neural Networks (CNN) through applications in image processing and classification.

Chapter 4, Data Representation Using Autoencoders, builds the foundation of autoencoder using multiple recipes and also covers the application in data compression and denoising.

Chapter 5, Generative Models in Deep learning, extends the concept of autoencoders to generative models and covers recipes such as Boltzman machines, restricted Boltzman machines (RBMs), and deep belief networks.

Chapter 6, Recurrent Neural Networks, sets up the foundation for building machine learning models on a sequential datasets using multiple recurrent neural networks (RNNs).

Chapter 7, Reinforcement Leaning, provides the fundamentals for building reinforcement learning using Markov Decision Process (MDP) and covers both model-based learning and model-free learning.

Chapter 8, Application of Deep Learning in Text-Mining, provides an end-to-end implementation of the deep learning text mining domain.

Chapter 9, Application of Deep Learning to Signal processing, covers a detailed case study of deep learning in the signal processing domain.

Chapter 10, Transfer Learning, covers recipes for using pretrained models such as VGG16 and Inception and explains how to deploy a deep learning model using GPU.