Representation Learning: A Review and New Perspectives
Why is this work in the frame?
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
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.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
The record
- Venue
- IEEE Transactions on Pattern Analysis and Machine Intelligence
- Topic
- Face and Expression Recognition
- Field
- Computer Science
- Canadian institutions
- Université de Montréal
- Funders
- —
- 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
- Has abstract in OpenAlex
- yes