Deep generative neural networks are a popular form of unsupervised deep learning models. These models aim to learn the process that generates the data. Generative models not only learn to extract patterns from the data but also estimate the underlying probability distribution. These models are used to create synthetic data, which follows the same probability distribution as that of the given training dataset. This chapter will give you an idea of deep generative models and how they work.
In this chapter, we will cover the following recipes:
- Generating images with GANs
- Implementing DCGANs
- Implementing variational autoencoders
