Preface

For years, those who have been faithfully working on machine learning have seen the field grow and flourish, yielding amazing technology and even promising radical societal changes. However, for those who want to join us in studying this area, it might seem a little bit intimidating. Certainly, there is so much stuff out there on the web and it has become very difficult to navigate through all the papers, and the code, to find reliable introductory content for those who want to join us in the field of deep learning. While there are many introductory books on machine learning, most are inadequate in addressing the needs of those who specifically want to work on deep learning and have the minimum necessary mathematical, algorithmic, and programming skills.

This book aims to reach out to those beginners in deep learning who are looking for a strong foundation in the basic concepts required to build deep learning models using well-known methodologies. If that sounds like you, then this book might be what you need. The book assumes no prior extensive exposure to neural networks and deep learning and starts by reviewing the machine learning fundamentals needed for deep learning. Then, it explains how to prepare data by cleaning and preprocessing it for deep learning and gradually goes on to introduce neural networks and the popular supervised neural network architectures, such as convolutional neural networks (CNNs), recurrent neural networks (RNNs), and generative adversarial networks (GANs), and unsupervised architectures, such as autoencoders (AEs), variational autoencoders (VAEs), and restricted Boltzmann machines (RBMs). At the end of each chapter, you will have a chance to test your understanding of the concepts and reflect on your own growth.

By the end of the book, you will have an understanding of deep learning concepts and recipes and will be able to distinguish which algorithms are appropriate for different tasks.