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
Parents
2.3K
Gaussian Error Linear Units (GELUs)
Dan Hendrycks, Kevin Gimpel · arXiv (Cornell University) · 2016 · 3.2K citations · Full text
Deep Learning using Rectified Linear Units (ReLU)
Abien Fred Agarap · arXiv (Cornell University) · 2018 · 2.5K citations · Full text
1–5 of 2.3K
5.9K
30
h-index
26
h-index
21
h-index
20
h-index
14
h-index
1–5 of 5.9K
1.8K

Southeast University
Nanjing, China
36 h-index
105 publications
6.2K citations
Chinese University of Hong Kong
Hong Kong, Hong Kong
27 h-index
63 publications
6.6K citations

Hunan University
Changsha, China
25 h-index
75 publications
3K citations

City University of Hong Kong
Hong Kong, Hong Kong
23 h-index
33 publications
2.5K citations
Hunan Normal University
Changsha, China
21 h-index
76 publications
3.4K citations

Huazhong University of Science and Technology
Wuhan, China
20 h-index
52 publications
4.6K citations
Fudan University
Shanghai, China
20 h-index
40 publications
3.9K citations
Massachusetts Institute of Technology
Cambridge, United States
19 h-index
45 publications
4.5K citations
1–8 of 1.8K
Repository · 240 publications · 26.1K citations
57
h-index
87 publications · 13.9K citations
50
h-index
85 publications · 7K citations
47
h-index
52 publications · 3.7K citations
31
h-index
36 publications · 5.2K citations
30
h-index
1–5