Hierarchical Representation Learning

Hierarchical Representation Learning is a representation learning framework that organizes learned features into multiple levels of abstraction, where higher layers capture increasingly complex and invariant patterns through a structured composition of simpler features from lower layers.

625

Publications

60K

Citations

2.1K

Authors

665

Institutions

Publications per year

2017–2026

400

Authors

2.1K

  1. GE
    Geoffrey E. Hinton

    University of Toronto, Canada

    9 publications · 930 citations

    9

    h-index

  2. HL
    Honglak Lee

    University of Michigan, United States

    8 publications · 4K citations

    8

    h-index

  3. TP
    Tomaso Poggio

    Massachusetts Institute of Technology, United States

    8 publications · 535 citations

    8

    h-index

  4. JF
    Jianping Fan

    University of North Carolina at Charlotte, United States

    8 publications · 241 citations

    8

    h-index

  5. LR
    Lorenzo Rosasco

    University of Genoa, Italy

    7 publications · 197 citations

    7

    h-index

1–5 of 2.1K

Venues

  1. arXiv (Cornell University)

    Repository · 78 publications · 4.5K citations

    36

    h-index

  2. IEEE Transactions on Image Processing

    21 publications · 2.5K citations

    19

    h-index

  3. 12

    h-index

  4. Proceedings of the AAAI Conference on Artificial Intelligence

    Conference · 11 publications · 1.3K citations

    11

    h-index

  5. Neurocomputing

    12 publications · 294 citations

    11

    h-index

1–5