Generate a confrontation network (Gan:generative adversarial Networks)

Thesis: Goodfellow, Ian, et al. "Generative adversarial nets." Advances in neural information processing Systems. 2014.

The two-person zero-sum game in Gan-inspired game theory, pioneered by [Goodfellow et al, NIPS 2014], contains a generative model (generative) and a discriminant model (discriminative models D). The generation model captures the distribution of sample data, and the discriminant model is a two classifier to determine whether the input is a real or a generated sample. The optimization process of this model is a "two-yuan Minimax game (minimax two-player game)" problem, the training fixed one side, update the other model parameters, alternating iterations, so that each other's error maximization, finally, G can estimate the distribution of sample data. When training D is to minimize the error of the discriminant model, training G is the maximum discriminant model error.

REF:

http://blog.csdn.net/solomon1558/article/details/52537114

http://blog.csdn.net/shenxiaolu1984/article/details/52215983

http://blog.csdn.net/layumi1993/article/details/52328594

Http://www.wtoutiao.com/p/172tUtn.html introduced some theoretical developments and applications of Gan (such as gan->cgan->lapgan->dcgan->gran-> Vaegan, etc.)