Representation Learning: A Review and New Perspectives

  title={Representation Learning: A Review and New Perspectives},
  author={Yoshua Bengio and Aaron C. Courville and P. Vincent},
  journal={IEEE Transactions on Pattern Analysis and Machine Intelligence},
  • Yoshua Bengio, Aaron C. Courville, P. Vincent
  • Published 2013
  • Computer Science, Mathematics, Medicine
  • IEEE Transactions on Pattern Analysis and Machine Intelligence
  • 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… CONTINUE READING
    A Modular Theory of Feature Learning
    • 4
    • PDF
    An Overview on Data Representation Learning: From Traditional Feature Learning to Recent Deep Learning
    • 58
    • PDF
    Sparse, hierarchical and shared-factors priors for representation learning
    Representational learning for sonar ATR
    • 7
    Deep Dimension Reduction for Supervised Representation Learning
    Learning Deep Representation Without Parameter Inference for Nonlinear Dimensionality Reduction
    • X. Zhang
    • Computer Science, Mathematics
    • 2013
    • 1
    • Highly Influenced
    • PDF


    Publications referenced by this paper.
    Unsupervised and Transfer Learning Challenge: a Deep Learning Approach
    • 188
    • PDF
    Deep Learning of Representations for Unsupervised and Transfer Learning
    • 775
    • PDF
    Sparse Feature Learning for Deep Belief Networks
    • 726
    • PDF
    The Manifold Tangent Classifier
    • 220
    • PDF
    Understanding Representations Learned in Deep Architectures
    • 85
    • PDF
    Large-Scale Learning of Embeddings with Reconstruction Sampling
    • 41
    • PDF
    Why Does Unsupervised Pre-training Help Deep Learning?
    • 1,177
    • PDF
    Extracting and composing robust features with denoising autoencoders
    • 4,026
    • PDF
    On deep generative models with applications to recognition
    • 193
    • PDF