Recurrent Neural Networks

Recurrent Neural Networks is a type of neural network architecture characterized by directed cycles in its connections, enabling the model to maintain an internal state that captures temporal dynamics and process sequences of variable length through recursive application of shared parameters over time steps.

10.2K

Publications

1M

Citations

26.3K

Authors

4.5K

Institutions

Publications per year

2017–2026

6.5K

Authors

26.3K

  1. JW
    Jun Wang

    Chinese University of Hong Kong, Hong Kong SAR China

    124 publications · 13.5K citations

    67

    h-index

  2. YB
    Yoshua Bengio

    Université de Montréal, Canada

    82 publications · 39.3K citations

    45

    h-index

  3. JS
    Jürgen Schmidhuber

    Dalle Molle Institute for Artificial Intelligence Research, Switzerland

    39 publications · 125.1K citations

    34

    h-index

  4. JC
    Jinde Cao

    Southeast University, China

    38 publications · 3.9K citations

    32

    h-index

  5. CL
    C. Lee Giles

    Pennsylvania State University, United States

    49 publications · 4.5K citations

    31

    h-index

1–5 of 26.3K

Venues

  1. arXiv (Cornell University)

    Repository · 1K publications · 118.5K citations

    143

    h-index

  2. IEEE Transactions on Neural Networks

    195 publications · 42K citations

    84

    h-index

  3. 72

    h-index

  4. IEEE Access

    257 publications · 22.1K citations

    71

    h-index

  5. Neural Computation

    132 publications · 124.9K citations

    59

    h-index

1–5