Representation Learning: A Review and New Perspectives
Y. Bengio and A. Courville and P. Vincent

Type: Paper

author={Y. Bengio and A. Courville and P. Vincent},
journal={IEEE Transactions on Pattern Analysis and Machine Intelligence},
title={Representation Learning: A Review and New Perspectives},
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 intelligence;data structures;probability;unsupervised learning;AI;autoencoders;data representation;density estimation;geometrical connections;machine learning algorithms;manifold learning;probabilistic models;representation learning;unsupervised feature learning;Abstracts;Feature extraction;Learning systems;Machine learning;Manifolds;Neural networks;Speech recognition;Boltzmann machine;Deep learning;autoencoder;feature learning;neural nets;representation learning;unsupervised learning;Algorithms;Artificial Intelligence;Humans;Neural Networks (Computer)},

Send Feedback