Activation Functions

Activation Function is a mathematical function applied to the output of a neuron in a neural network that determines the neuron's activation level by introducing non-linear decision boundaries, enabling the model to learn complex patterns.

2.3K

Publications

157.1K

Citations

5.9K

Authors

1.8K

Institutions

Publications per year

2017–2026

1.3K

Authors

5.9K

  1. JC
    Jinde Cao

    Southeast University, China

    40 publications · 2.9K citations

    30

    h-index

  2. JW
    Jun Wang

    Chinese University of Hong Kong, Hong Kong SAR China

    27 publications · 3.2K citations

    26

    h-index

  3. LX
    Lin Xiao

    Hunan Normal University, China

    25 publications · 1.5K citations

    21

    h-index

  4. ZZ
    Zhigang Zeng

    Huazhong University of Science and Technology, China

    21 publications · 2.2K citations

    20

    h-index

  5. XN
    Xiaobing Nie

    Southeast University, China

    15 publications · 720 citations

    14

    h-index

1–5 of 5.9K

Venues

  1. arXiv (Cornell University)

    Repository · 240 publications · 26.1K citations

    57

    h-index

  2. IEEE Transactions on Neural Networks

    87 publications · 13.9K citations

    50

    h-index

  3. 47

    h-index

  4. Neurocomputing

    52 publications · 3.7K citations

    31

    h-index

  5. Neural Networks

    36 publications · 5.2K citations

    30

    h-index

1–5