We value your privacy
This site uses cookies to improve your browsing experience, analyze site traffic, and show personalized content.
A generative adversarial network (GAN) is a class of machine learning frameworks and a prominent framework for approaching generative artificial intelligence.[1][2] The concept was initially developed by Ian Goodfellow and his colleagues in June 2014.[3] In a GAN, two neural networks contest with each other in the form of a zero-sum game, where one agent's gain is another agent's loss.