Autoencoding

Autoencoding is a self-supervised learning framework that belongs to the class of representation learning methods, distinguished by its use of a neural network architecture configured to reconstruct its input data through an information bottleneck, thereby learning efficient codings of the input distribution without requiring labeled data.

250

Publications

23.4K

Citations

864

Authors

297

Institutions

Publications per year

2017–2026

204

Authors

864

  1. YB
    Yoshua Bengio

    Université de Montréal, Canada

    11 publications · 2.2K citations

    11

    h-index

  2. GQ
    Guo-Jun Qi

    University of Central Florida, United States

    5 publications · 366 citations

    5

    h-index

  3. LF
    Liang Feng

    Chongqing University, China

    5 publications · 830 citations

    5

    h-index

  4. YO
    Yew-Soon Ong

    Nanyang Technological University, Singapore

    5 publications · 1.5K citations

    5

    h-index

  5. LZ
    Liheng Zhang

    University of Central Florida, United States

    4 publications · 333 citations

    4

    h-index

1–5 of 864

Venues

  1. arXiv (Cornell University)

    Repository · 55 publications · 5.4K citations

    29

    h-index

  2. Proceedings of the AAAI Conference on Artificial Intelligence

    Conference · 6 publications · 383 citations

    6

    h-index

  3. IEEE Transactions on Cybernetics

    5 publications · 706 citations

    5

    h-index

  4. IEEE Access

    5 publications · 90 citations

    5

    h-index

  5. IEEE Transactions on Image Processing

    4 publications · 498 citations

    4

    h-index

1–5