209 citations · 361 across the 6 of their papers we have counts for
6 papers
Better Mixing via Deep Representations
Yoshua Bengio, Grégoire Mesnil, Yann Dauphin +1
It has previously been hypothesized, and supported with some experimental evidence, that deeper representations, when well trained, tend to do a better job at disentangling the und…
Implicit Density Estimation by Local Moment Matching to Sample from Auto-Encoders
Yoshua Bengio, Guillaume Alain, Salah Rifai
Recent work suggests that some auto-encoder variants do a good job of capturing the local manifold structure of the unknown data generating density. This paper contributes to the m…
A Generative Process for Sampling Contractive Auto-Encoders
Salah Rifai, Yoshua Bengio, Yann Dauphin +1
The contractive auto-encoder learns a representation of the input data that captures the local manifold structure around each data point, through the leading singular vectors of th…
Learning invariant features through local space contraction
Salah Rifai, Xavier Muller, Xavier Glorot +3
We present in this paper a novel approach for training deterministic auto-encoders. We show that by adding a well chosen penalty term to the classical reconstruction cost function,…
Adding noise to the input of a model trained with a regularized objective
Salah Rifai, Xavier Glorot, Yoshua Bengio +1
Regularization is a well studied problem in the context of neural networks. It is usually used to improve the generalization performance when the number of input samples is relativ…
Deep Self-Taught Learning for Handwritten Character Recognition
Frédéric Bastien, Yoshua Bengio, Arnaud Bergeron +14
Recent theoretical and empirical work in statistical machine learning has demonstrated the importance of learning algorithms for deep architectures, i.e., function classes obtained…