Autoencoders

Autoencoders is a neural network model designed for unsupervised learning that consists of an encoder that compresses input data into a lower-dimensional latent representation and a decoder that reconstructs the original input from this representation, thereby enabling dimensionality reduction and representation learning through the minimization of reconstruction error.

3.6K

Publications

307.9K

Citations

13.8K

Authors

2.4K

Institutions

Publications per year

2017–2026

3.2K

Authors

13.8K

  1. MW
    Max Welling

    University of Amsterdam, Netherlands

    20 publications · 4.9K citations

    17

    h-index

  2. YB
    Yoshua Bengio

    Université de Montréal, Canada

    20 publications · 14.8K citations

    16

    h-index

  3. BW
    Björn W. Schuller

    Imperial College London, United Kingdom

    11 publications · 925 citations

    11

    h-index

  4. YL
    Yann LeCun

    New York University, United States

    12 publications · 1.6K citations

    11

    h-index

  5. LC
    Lawrence Carin

    Duke University, United States

    12 publications · 1.2K citations

    11

    h-index

1–5 of 13.8K

Venues

  1. arXiv (Cornell University)

    Repository · 586 publications · 43K citations

    99

    h-index

  2. IEEE Access

    95 publications · 6.2K citations

    40

    h-index

  3. 36

    h-index

  4. 32

    h-index

  5. Proceedings of the AAAI Conference on Artificial Intelligence

    Conference · 54 publications · 3.1K citations

    28

    h-index

1–5