IEEE Transactions on Pattern Analysis and Machine Intelligence· 2013Q1· Review
Representation Learning: A Review and New Perspectives
- 13,077citations
- Q1SCImago
- 2013year
Short summary
This review posits that machine learning success hinges on data representation, hypothesizing that better representations disentangle explanatory factors of variation, and surveys unsupervised feature learning and deep learning advances.
AI-generated from the title and abstract; the full text is not read.
Key points
- Machine learning success is hypothesized to depend on data representation's ability to disentangle explanatory factors.
- The paper reviews advances in unsupervised feature learning and deep learning.
- Covered areas include probabilistic models, autoencoders, manifold learning, and deep networks.
- Key open questions concern learning objectives, inference, and geometric connections to density estimation and manifold learning.
AI-generated from the title and abstract; the full text is not read.
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.
The authors' abstract, as published at the source. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2013 · DOI ↗
Continue with a free account
Ask the paper: 3 free questions a day about this paper; save it, get its citation, new summaries every day for your field. Takeaways are Premium.
Continue free on the webSign in with Google or Apple; no card needed. You come back to this paper.
On your phone:
Field: Computer Vision and Pattern Recognition
Computer Vision and Pattern RecognitionComputer Science