Attractor Networks

Attractor Networks is a type of recurrent neural network model distinguished by its dynamical property of converging to stable states, or attractors, which represent stored memories or patterns through fixed-point, cyclic, or chaotic trajectories in state space.

784

Publications

61.8K

Citations

1.8K

Authors

784

Institutions

Publications per year

2017–2026

234

Variants

Attractor Neural Networks

Authors

1.8K

  1. ET
    Edmund T. Rolls

    University of Oxford, United Kingdom

    36 publications · 2.3K citations

    28

    h-index

  2. GD
    Gustavo Deco

    Universitat Pompeu Fabra, Spain

    21 publications · 2.2K citations

    20

    h-index

  3. AL
    Anders Lansner

    KTH Royal Institute of Technology, Sweden

    21 publications · 935 citations

    16

    h-index

  4. DJ
    Daniel J. Amit

    Hebrew University of Jerusalem, Israel

    16 publications · 1.3K citations

    15

    h-index

  5. AT
    Alessandro Treves

    Scuola Internazionale Superiore di Studi Avanzati, Italy

    16 publications · 969 citations

    15

    h-index

1–5 of 1.8K

Venues

  1. Network Computation in Neural Systems

    41 publications · 2.6K citations

    27

    h-index

  2. Neural Computation

    29 publications · 5.8K citations

    24

    h-index

  3. PLoS Computational Biology

    27 publications · 2.3K citations

    22

    h-index

  4. Journal of Neuroscience

    22 publications · 5.3K citations

    20

    h-index

  5. Proceedings of the National Academy of Sciences

    PNAS · 18 publications · 4K citations

    18

    h-index

1–5