Réseaux de neurones à relaxation entraînés par critère d'autoencodeur débruitant

By F. Savard. 2012

Subfields: Generative Models

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Generative Models

1. Yoshua Bengio
2. L. Yao
3. Pascal Vincent
4. Stefano Ermon
5. Aaron C. Courville
6. Guillaume Alain
7. Jason Yosinski
8. Jiaming Song

Citations in the corpus

• GSNs : Generative Stochastic Networks (2015, methodology): “To emulate a sampling procedure similar to Boltzmann machines in which the filled-in missing values can depend on the representations at the top level, the computational graph allows information to propagate both upwards (from input to higher levels) and downwards, giving rise to the computational g”
• Representation Learning: A Review and New Perspectives (2012, methodology): “We have performed preliminary exploration [179] of deterministic variants of deep autoencoders whose computational graph is similar to that of a DBM (in fact very close to the meanfield variational approximations associated with the Boltzmann machine), and that is one interesting intermediate point ”