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}
}
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
29 Citations
Modeling Dynamics with Deep Transition-Learning Networks
Generalization of iterative sampling in autoencoders
  • Highly Influenced
  • PDF
Generative Modeling by Estimating Gradients of the Data Distribution
  • 107
  • PDF
Maximum Reconstruction Estimation for Generative Latent-Variable Models
  • 1
  • PDF
Discrete Object Generation with Reversible Inductive Construction
  • 9
  • PDF
Unregularized Auto-Encoder with Generative Adversarial Networks for Image Generation
  • 5
Transportation analysis of denoising autoencoders: a novel method for analyzing deep neural networks
  • 4
  • PDF
Learning robust features by extended generative stochastic networks
Conservativeness of Untied Auto-Encoders
  • 6
  • PDF
...
1
2
3
...

References

SHOWING 1-10 OF 81 REFERENCES
Deep Generative Stochastic Networks Trainable by Backprop
  • 317
  • PDF
Multimodal Transitions for Generative Stochastic Networks
  • 10
  • PDF
Generalized Denoising Auto-Encoders as Generative Models
  • 373
  • PDF
Generative Adversarial Nets
  • 21,507
  • PDF
On the Equivalence between Deep NADE and Generative Stochastic Networks
  • 8
  • PDF
A Generative Process for sampling Contractive Auto-Encoders
  • 65
Deep AutoRegressive Networks
  • 193
  • PDF
Estimating or Propagating Gradients Through Stochastic Neurons
  • 61
  • PDF
Deep Unsupervised Learning using Nonequilibrium Thermodynamics
  • 126
  • PDF
General Stochastic Networks for Classification
  • 21
  • PDF
...
1
2
3
4
5
...