Description
Generative Adversarial Networks (GANs) are a promising framework for unsupervised learning. GANs consist of a generator and a discriminator, which learn together by pursuing competing goals. From a conceptual perspective, adversarial training is fascinating because it bypasses the need of loss functions in learning, and opens the door to new ways of regularizing (as well as fooling or attacking) learning machines. In this talk GANs basics are explained and a lot of examples of their usage are provided.