Residual Layer

Residual Layer is a neural network layer architecture that belongs to the category of deep learning building blocks, distinguished by its inclusion of a skip connection that enables the direct propagation of inputs to subsequent layers, thereby facilitating the training of deeper networks by mitigating gradient vanishing problems.

501

Publications

313.7K

Citations

1.9K

Authors

637

Institutions

Publications per year

2017–2026

363

Variants

Residual Block

Authors

1.9K

  1. HS
    Helmut Schift

    Paul Scherrer Institute, Switzerland

    4 publications · 84 citations

    4

    h-index

  2. BB
    B. B. Balsley

    University of Colorado Boulder, United States

    4 publications · 273 citations

    4

    h-index

  3. GT
    Guiqian Tang

    Institute of Atmospheric Physics, China

    4 publications · 280 citations

    4

    h-index

  4. HH
    Hiroshi Hiroshima

    National Institute of Advanced Industrial Science and Technology, Japan

    4 publications · 95 citations

    4

    h-index

  5. BL
    B. L. Lefer

    University of Houston, United States

    4 publications · 380 citations

    4

    h-index

1–5 of 1.9K

Venues

  1. arXiv (Cornell University)

    Repository · 60 publications · 12.7K citations

    34

    h-index

  2. IEEE Access

    19 publications · 531 citations

    14

    h-index

  3. Microelectronic Engineering

    9 publications · 166 citations

    9

    h-index

  4. Neurocomputing

    8 publications · 404 citations

    8

    h-index

  5. 8

    h-index

1–5