Paper notes: Generative adversarial Nets

Generative adversarial Nets

NIPS 2014

In this paper, a new framework is proposed to predict the production model through the process of confrontation, and we train two models: a production model G, which can catch the data distribution, and a discriminant model D can predict the probability of a sample from a training sample instead of G. The purpose of training G is to make D as error-making as possible, to make it impossible to tell whether an image is produced or from a training sample. The framework corresponds to the

Paper notes: Generative adversarial Nets