Representation Learning: A Review and New Perspectives

@article{Bengio2013RepresentationLA,
  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},
  year={2013},
  volume={35},
  pages={1798-1828}
}
  • 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
    View on IEEE
    arxiv.org
    Top 3 of 6,257 Citations
    A Modular Theory of Feature Learning
    D. McNamara, Cheng Soon Ong, R. WilliamsonArXiv2016
    4
    The Role of the Information Bottleneck in Representation Learning
    Matías Vera, P. Piantanida, L. Vega2018 IEEE International Symposium on Information Theory (ISIT)2018
    13
    An Overview on Data Representation Learning: From Traditional Feature Learning to Recent Deep Learning
    Guoqiang Zhong, Lina Wang, J. DongArXiv2016
    58

    Supplemental Code

    GITHUB REPO
    Via Papers with Code
    saromanov/godownload
    Download files as in wget :file_folder:
    5 Stars • 1 Forks
    Explore Further
    Discover more papers related to the topics discussed in this paper
    6,257 Citations
    Citation Type

    Citation Type

    A Modular Theory of Feature Learning
    • 4
    • PDF
    The Role of the Information Bottleneck in Representation Learning
    • 13
    An Overview on Data Representation Learning: From Traditional Feature Learning to Recent Deep Learning
    • 58
    • PDF
    Autonomous Learning of Representations
    • 2
    • PDF
    Sparse, hierarchical and shared-factors priors for representation learning
    Learning deep representations by mutual information estimation and maximization
    • 425
    • PDF
    Representational learning for sonar ATR
    • 7
    An analysis on the use of autoencoders for representation learning: fundamentals, learning task case studies, explainability and challenges
    • 2
    • PDF
    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

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 287 REFERENCES
    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
    A Generative Process for sampling Contractive Auto-Encoders
    • 63
    On deep generative models with applications to recognition
    • 193
    • PDF