Book Image

Hands-On Generative Adversarial Networks with Keras

By : Rafael Valle
Book Image

Hands-On Generative Adversarial Networks with Keras

By: Rafael Valle

Overview of this book

Generative Adversarial Networks (GANs) have revolutionized the fields of machine learning and deep learning. This book will be your first step toward understanding GAN architectures and tackling the challenges involved in training them. This book opens with an introduction to deep learning and generative models and their applications in artificial intelligence (AI). You will then learn how to build, evaluate, and improve your first GAN with the help of easy-to-follow examples. The next few chapters will guide you through training a GAN model to produce and improve high-resolution images. You will also learn how to implement conditional GANs that enable you to control characteristics of GAN output. You will build on your knowledge further by exploring a new training methodology for progressive growing of GANs. Moving on, you'll gain insights into state-of-the-art models in image synthesis, speech enhancement, and natural language generation using GANs. In addition to this, you'll be able to identify GAN samples with TequilaGAN. By the end of this book, you will be well-versed with the latest advancements in the GAN framework using various examples and datasets, and you will have developed the skills you need to implement GAN architectures for several tasks and domains, including computer vision, natural language processing (NLP), and audio processing. Foreword by Ting-Chun Wang, Senior Research Scientist, NVIDIA
Table of Contents (14 chapters)
Free Chapter
Section 1: Introduction and Environment Setup
Section 2: Training GANs
Section 3: Application of GANs in Computer Vision, Natural Language Processing, and Audio

Discriminative and generative models compared

Broadly speaking, machine learning models can be subdivided into discriminative models and generative models. Discriminative models learn a map from some input to some output. In discriminative models, learning the process that generates the input is not relevant; it will just learn a map from the to the expected output.

Generative models, on the other hand, in addition to learning a map from some input to some output, also learn the process that generates the input and the output.

Source: Ian Goodfellow's Tutorial on Generative Adversarial Networks, 2017

In this context, we say that discriminative models estimate : the conditional probability distribution of conditioned on . Note that, in this case, the input x is fixed, known a priori, and the discriminative model estimates the probability of , , but does not have any information...