A generative adversarial network (GAN) is a class of machine learning [Machine learning] frameworks and a prominent framework for approaching generative AI. The concept was initially developed by Ian Goodfellow and his colleagues in June 2014. In a GAN, two neural networks contest with each other in the form of a zero-sum game [Zero-sum game], where one agent’s gain is another agent’s loss.


GANs are similar to mimicry in evolutionary biology, with an evolutionary arms race between both networks.

(“Generative Adversarial Network” 2023)



“Generative Adversarial Network.” 2023. Wikipedia, January. https://en.wikipedia.org/w/index.php?title=Generative_adversarial_network&oldid=1132368875.