In this chapter, we will discuss how Generative Adversarial Networks (GANs) are used for deep learning in domains where the key method is to train an image generator by simultaneously training a discriminator to challenge the latter for improvement. The same method can be applied to domains different from Images. In addition, we will discuss the Variational Autoencoder.
GANs have been defined as the most interesting idea in the last 10 years in ML (https://www.quora.com/What-are-some-recent-and-potentially-upcoming-breakthroughs-in-deep-learning) by Yann LeCun, one of the fathers of Deep Learning. GANs are able to learn how to reproduce synthetic data which looks real. For instance, computers can learn how to paint and create realistic images. The idea was originally proposed by Ian Goodfellow who worked with the University of Montreal, Google Brain, and recently...
