Sciweavers

Share
ICML
2008
IEEE

Extracting and composing robust features with denoising autoencoders

9 years 11 months ago
Extracting and composing robust features with denoising autoencoders
Previous work has shown that the difficulties in learning deep generative or discriminative models can be overcome by an initial unsupervised learning step that maps inputs to useful intermediate representations. We introduce and motivate a new training principle for unsupervised learning of a representation based on the idea of making the learned representations robust to partial corruption of the input pattern. This approach can be used to train autoencoders, and these denoising autoencoders can be stacked to initialize deep architectures. The algorithm can be motivated from a manifold learning and information theoretic perspective or from a generative model perspective. Comparative experiments clearly show the surprising advantage of corrupting the input of autoencoders on a pattern classification benchmark suite.
Pascal Vincent, Hugo Larochelle, Yoshua Bengio, Pi
Added 17 Nov 2009
Updated 17 Nov 2009
Type Conference
Year 2008
Where ICML
Authors Pascal Vincent, Hugo Larochelle, Yoshua Bengio, Pierre-Antoine Manzagol
Comments (0)
books