A good paper to better understand GANs is Generative Adversarial Networks (2014) by Ian J. Goodfellow, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron Courville, Yoshua Bengio. In this recipe, we will learn how to forge MNIST handwritten numbers by using fully-connected layer networks organized in a Generator-Discriminator architecture.