Ian Goodfellow led the coauthored 2014 paper introducing generative adversarial networks. A generator transforms a noise input into a sample, while a discriminator attempts to distinguish generated samples from training examples. Training sets up a two-player minimax objective rather than directly requiring a tractable probability density for every generated observation.[ref]
The original objective isAlternating updates seek to improve each player against the other, but the idealized equilibrium analysis does not guarantee that a practical finite neural network training run converges. Goodfellow also coauthored Deep Learning by Ian Goodfellow and others with Yoshua Bengio and Aaron Courville.
New to topics? Read the docs here!