jinbeibei0606的博客

reference: http://blog.youkuaiyun.com/u013139259/article/details/53590536所谓的对抗网络可以归结为unsupervised learning 或者 generative model。从无监督学习来进行feature representation,有k-means聚类算法，auto-encoders[2]，以及09年的Deep belief