Extracting and composing robust features with denoising autoencoders

  title={Extracting and composing robust features with denoising autoencoders},
  author={Pascal Vincent and Hugo Larochelle and Yoshua Bengio and Pierre-Antoine Manzagol},
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… CONTINUE READING
Highly Influential
This paper has highly influenced 246 other papers. REVIEW HIGHLY INFLUENTIAL CITATIONS
Highly Cited
This paper has 3,478 citations. REVIEW CITATIONS


Publications citing this paper.
Showing 1-10 of 1,791 extracted citations

Denoising Sparse Autoencoder-Based Ictal EEG Classification

IEEE Transactions on Neural Systems and Rehabilitation Engineering • 2018
View 11 Excerpts
Highly Influenced

A Graph Regularized Deep Neural Network for Unsupervised Image Representation Learning

2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) • 2017
View 11 Excerpts
Highly Influenced

A novel multi-variate analysis method for searching particles in high energy physics

2017 13th International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery (ICNC-FSKD) • 2017
View 10 Excerpts
Highly Influenced

Ments through Corruption

View 6 Excerpts
Highly Influenced

3,478 Citations

Citations per Year
Semantic Scholar estimates that this publication has 3,478 citations based on the available data.

See our FAQ for additional information.


Publications referenced by this paper.
Showing 1-2 of 2 references

Learning deep architectures for AI (Technical Report 1312)

Y. Bengio
Université de Montréal, dept. IRO • 2007
View 10 Excerpts
Highly Influenced

Similar Papers

Loading similar papers…