Representation Learning: A Review and New Perspectives
@article{Bengio2013RepresentationLA, title={Representation Learning: A Review and New Perspectives}, author={Yoshua Bengio and Aaron C. Courville and P. Vincent}, journal={IEEE Transactions on Pattern Analysis and Machine Intelligence}, year={2013}, volume={35}, pages={1798-1828} }
The success of machine learning algorithms generally depends on data representation, and we hypothesize that this is because different representations can entangle and hide more or less the different explanatory factors of variation behind the data. Although specific domain knowledge can be used to help design representations, learning with generic priors can also be used, and the quest for AI is motivating the design of more powerful representation-learning algorithms implementing such priors… CONTINUE READING
Supplemental Code
Paper Mentions
6,743 Citations
An Overview on Data Representation Learning: From Traditional Feature Learning to Recent Deep Learning
- Computer Science, Mathematics
- ArXiv
- 2016
- 70
- Highly Influenced
- PDF
The Role of the Information Bottleneck in Representation Learning
- Computer Science
- 2018 IEEE International Symposium on Information Theory (ISIT)
- 2018
- 17
Learning deep representations by mutual information estimation and maximization
- Computer Science, Mathematics
- ICLR
- 2019
- 534
- PDF
An analysis on the use of autoencoders for representation learning: fundamentals, learning task case studies, explainability and challenges
- Computer Science, Mathematics
- Neurocomputing
- 2020
- 4
- PDF
Representational learning for sonar ATR
- Engineering, Computer Science
- Defense + Security Symposium
- 2014
- 7
Deep Dimension Reduction for Supervised Representation Learning
- Computer Science, Mathematics
- ArXiv
- 2020
- PDF
References
SHOWING 1-10 OF 284 REFERENCES
Unsupervised and Transfer Learning Challenge: a Deep Learning Approach
- Computer Science
- ICML Unsupervised and Transfer Learning
- 2012
- 193
- PDF
Deep Learning of Representations for Unsupervised and Transfer Learning
- Computer Science
- ICML Unsupervised and Transfer Learning
- 2012
- 839
- PDF
Extracting and composing robust features with denoising autoencoders
- Mathematics, Computer Science
- ICML '08
- 2008
- 4,281
- PDF
A Generative Process for sampling Contractive Auto-Encoders
- Computer Science, Mathematics
- ICML 2012
- 2012
- 65