Gaussian Transfer Functions

Gaussian Transfer Functions is a class of smooth, bell-shaped transfer functions used in signal processing and neural networks that are distinguished by their formulation based on the Gaussian probability density function, enabling localized, continuous, and differentiable mappings between input and output spaces.

24

Publications

1.1K

Citations

64

Authors

36

Institutions

Publications per year

2017–2026

1

Authors

64

  1. LL
    Lennart Ljung

    Linköping University, Sweden

    2 publications · 468 citations

    2

    h-index

  2. MD
    Mingyue Ding

    Huazhong University of Science and Technology, China

    2 publications · 86 citations

    2

    h-index

  3. HC
    Héloïse Cardinal

    Centre Hospitalier de l’Université de Montréal, Canada

    2 publications · 86 citations

    2

    h-index

  4. TC
    Tianshi Chen

    Linköping University, Sweden

    2 publications · 468 citations

    2

    h-index

  5. AF
    Aaron Fenster

    Western University, Canada

    2 publications · 86 citations

    2

    h-index

1–5 of 64

Venues

  1. European Journal of Inorganic Chemistry

    1 publications · 41 citations

    1

    h-index

  2. Journal of the Optical Society of America

    JOSA · 1 publications · 10 citations

    1

    h-index

  3. International Journal of Neural Systems

    1 publications · 12 citations

    1

    h-index

  4. Journal of Modern Optics

    1 publications · 10 citations

    1

    h-index

  5. 1

    h-index

1–5