No self-introduction
Loading
Profile
Follow
codes (1)
Generation countermeasure network Gan
no vote
Generative model is a model that can generate more similar samples by learning training samples. Among all the generation models, the most potential one is generation adversarial networks (Gans). Gans is a kind of unsupervised machine learning, and its operation mode can be seen as a zero sum game in which two neural networks compete with each other. There are two such players in GaN. One is the generation model (g) and the other is the discrimination model (d). They have their own functions. The generating model is a sample generator, which inputs a noise / sample and then packages it into a realistic sample, that is, the output. The discriminant model is a two classifier (like 0-1 classifier) to judge whether the input sample is true or false. (is the output value greater than 0.5 or less than 0.5). Using Gan, we can get a lot of practical data for modeling.
zxwwes 0 0
1
No more~
Follows0
Fans0