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 Pascal 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… Expand
View on IEEE
arxiv.org
7,487 Citations
Highly Influential Citations
391
Background Citations
3,916
Methods Citations
1,124
Results Citations
39

7,487 Citations

Citation Type

Citation Type

A Modular Theory of Feature Learning
An Overview on Data Representation Learning: From Traditional Feature Learning to Recent Deep Learning
The Role of the Information Bottleneck in Representation Learning
Sparse, hierarchical and shared-factors priors for representation learning
For Manifold Learning, Deep Neural Networks can be Locality Sensitive Hash Functions
Learning deep representations by mutual information estimation and maximization
An analysis on the use of autoencoders for representation learning: fundamentals, learning task case studies, explainability and challenges
Autonomous Learning of Representations
Relation-Guided Representation Learning
Representational learning for sonar ATR
  • J. Isaacs
  • Computer Science, Engineering
  • Defense + Security Symposium
  • 2014
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 286 REFERENCES
Unsupervised and Transfer Learning Challenge: a Deep Learning Approach
Deep Learning of Representations for Unsupervised and Transfer Learning
  • Yoshua Bengio
  • Computer Science
  • ICML Unsupervised and Transfer Learning
  • 2012
Sparse Feature Learning for Deep Belief Networks
The Manifold Tangent Classifier
Extracting and composing robust features with denoising autoencoders
Understanding Representations Learned in Deep Architectures
Large-Scale Learning of Embeddings with Reconstruction Sampling
Why Does Unsupervised Pre-training Help Deep Learning?
A Generative Process for sampling Contractive Auto-Encoders
On deep generative models with applications to recognition
...
1
2
3
4
5
...