GSNs : Generative Stochastic Networks.
Information and Inference: A Journal of the IMA(2016)
摘要
We introduce a novel training principle for generative probabilistic models that is an alternative to maximum likelihood. The proposed Generative Stochastic Networks (GSNs) framework generalizes Denoising Auto-Encoders (DAEs), and is based on learning the transition operator of a Markov chain whose stationary distribution estimates the data distribution. The transition distribution is a conditiona...
更多查看译文
关键词
deep learning,auto-encoders,generative models
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要