Generative Deep Learning

Chapter 3. Variational Autoencoders

In 2013, Diederik P. Kingma and Max Welling published a paper that laid the foundations for a type of neural network known as a variational autoencoder (VAE).¹ This is now one of the most fundamental and well-known deep learning architectures for generative modeling. In this chapter, we shall start by building a standard autoencoder and then see how we can extend this framework to develop a variational autoencoder—our first example of a generative deep learning model.

Along the way, we will pick apart both types of model, to understand how they work at a granular level. By the end of the chapter you should have a complete understanding of how to build and manipulate autoencoder-based models and, in particular, how to build a variational autoencoder from scratch to generate images based on your own training set.

Let’s start by paying a visit to a strange art exhibition…

The Art Exhibition

Two brothers, Mr. N. Coder and Mr. D. Coder, run an art gallery. One weekend, they host an exhibition focused on monochrome studies of single-digit numbers. The exhibition is particularly strange because it contains only one wall and no physical artwork. When a new painting arrives for display, Mr. N. Coder simply chooses a point on the wall to represent the painting, places a marker at this point, then throws the original artwork away. When a customer requests to see the painting, Mr. D. Coder attempts to re-create the artwork using just the coordinates of ...