Generative Deep Learning, 2nd Edition

Chapter 1. Generative Modeling

Chapter Goals

In this chapter you will:

• Learn the key differences between generative and discriminative models.

• Understand the desirable properties of a generative model through a simple example.

• Learn about the core probabilistic concepts that underpin generative models.

• Explore the different families of generative models.

• Clone the codebase that accompanies this book, so that you can get started building generative models!

This chapter is a general introduction to the field of generative modeling.

We will start with a gentle theoretical introduction to generative modeling and see how it is the natural counterpart to the more widely studied discriminative modeling. We will then establish a framework that describes the desirable properties that a good generative model should have. We will also lay out the core probabilistic concepts that are important to know, in order to fully appreciate how different approaches tackle the challenge of generative modeling.

This will lead us naturally to the penultimate section, which lays out the six broad families of generative models that dominate the field today. The final section explains how to get started with the codebase that accompanies this book.

What Is Generative Modeling?

Generative modeling can be broadly defined as follows:

Generative modeling is a branch of machine learning that involves training a model to produce new data that is similar to a given dataset.

What does this mean in ...