Generative Adversarial Nets

Generative Adversarial Networks (GANs) are a framework for estimating generative models via an adversarial process. Two networks, a generator and a discriminator, are trained simultaneously. The generator creates new data instances, while the discriminator evaluates them for authenticity. These networks compete, pushing each other to improve. The generator learns to produce increasingly realistic data, and the discriminator becomes better at distinguishing fake from real data. This process leads to a generative model that can create data similar to the training data.