Seonglae ChoGenerative Adversarial Network
Have been demonstrated to cover less of the generation space in comparison to explicit likelihood models (Diffusion Model overcome this)
Learn how to generate samples by competing like a counterfeiter and police, advancing through mini-maximizing error loss
GAN Notion
GANs
Generative adversarial network
A generative adversarial network (GAN) is a class of machine learning frameworks designed by Ian Goodfellow and his colleagues in June 2014. 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.
https://en.wikipedia.org/wiki/Generative_adversarial_network
