309 citations · 896 across the 12 of their papers we have counts for
Showing 2013Show all
2 papers · 1 filter
cs.LG2013★ 309 cited
Deep Generative Stochastic Networks Trainable by Backprop
Yoshua Bengio, Éric Thibodeau-Laufer, Guillaume Alain +1
We introduce a novel training principle for probabilistic models that is an alternative to maximum likelihood. The proposed Generative Stochastic Networks (GSN) framework is based…
cs.LG2013★ 203 cited
Generalized Denoising Auto-Encoders as Generative Models
Yoshua Bengio, Li Yao, Guillaume Alain +1
Recent work has shown how denoising and contractive autoencoders implicitly capture the structure of the data-generating density, in the case where the corruption noise is Gaussian…