Abstract

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. This paper reviews recent work in the area of unsupervised feature learning and deep learning, covering advances in probabilistic models, autoencoders, manifold learning, and deep networks. This motivates longer term unanswered questions about the appropriate objectives for learning good representations, for computing representations (i.e., inference), and the geometrical connections between representation learning, density estimation, and manifold learning.

Keywords

Artificial intelligenceFeature learningComputer scienceMachine learningRepresentation (politics)InferenceNonlinear dimensionality reductionUnsupervised learningDeep learningPrior probabilityExternal Data RepresentationProbabilistic logicFeature (linguistics)Domain knowledgeActive learning (machine learning)Semi-supervised learningBayesian probabilityDimensionality reduction

Affiliated Institutions

Related Publications

Publication Info

Year
2013
Type
review
Volume
35
Issue
8
Pages
1798-1828
Citations
12373
Access
Closed

External Links

View on DOI.org

Social Impact

Altmetric
PlumX Metrics

Social media, news, blog, policy document mentions

Citation Metrics

12373
OpenAlex

Cite This

Yoshua Bengio, Aaron Courville, P. M. Durai Raj Vincent (2013). Representation Learning: A Review and New Perspectives. IEEE Transactions on Pattern Analysis and Machine Intelligence , 35 (8) , 1798-1828. https://doi.org/10.1109/tpami.2013.50

Identifiers

DOI
10.1109/tpami.2013.50