• DOI:10.1093/IMAIAI/IAW003
Corpus ID: 15263766

GSNs : Generative Stochastic Networks

@article{Alain2015GSNsG,
  title={GSNs : Generative Stochastic Networks},
  author={G. Alain and Yoshua Bengio and L. Yao and J. Yosinski and Eric Thibodeau-Laufer and Saizheng Zhang and Pascal Vincent},
  journal={ArXiv},
  year={2015},
  volume={abs/1503.05571}
}

• G. Alain, Yoshua Bengio, +4 authors Pascal Vincent
• Published 2015
• Computer Science, Mathematics
• ArXiv

We introduce a novel training principle for generative probabilistic models that is an alternative to maximum likelihood. The proposed Generative Stochastic Networks (GSN) framework generalizes Denoising Auto-Encoders (DAE) and is based on learning the transition operator of a Markov chain whose stationary distribution estimates the data distribution. The transition distribution is a conditional distribution that generally involves a small move, so it has fewer dominant modes and is unimodal in… Expand

View PDF on arXiv

Save to Library

Create Alert

Cite

Launch Research Feed