Methods › General › Activation Functions › SReLU
S-shaped ReLU
SReLU
Introduced by Xiaojie Jin et al. in Deep Learning with S-shaped Rectified Linear Activation Units
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
The S-shaped Rectified Linear Unit, or SReLU, is an activation function for neural networks. It learns both convex and non-convex functions, imitating the multiple function forms given by the two fundamental laws, namely the Webner-Fechner law and the Stevens law, in psychophysics and neural sciences. Specifically, SReLU consists of three piecewise linear functions, which are formulated by four learnable parameters.
The SReLU is defined as a mapping:
f(x) = tᵢʳ + aʳᵢ(xᵢ-tʳᵢ) if xᵢ ≥tʳᵢ f(x) = xᵢ if tʳᵢ > x > tᵢˡ f(x) = tᵢˡ + aˡᵢ(xᵢ-tˡᵢ) if xᵢ ≤tˡᵢ
where tˡᵢ, tʳᵢ and aˡᵢ are learnable parameters of the network i and indicates that the SReLU can differ in different channels. The parameter aʳᵢ represents the slope of the right line with input above a set threshold. tʳᵢ and tˡᵢ are thresholds in positive and negative directions respectively.
Source: Activation Functions
Papers archive 2025-07-28
2 shown of 2, newest first. Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code; it is per sample and not a correctness claim.
-
Overcoming Overfitting and Large Weight Update Problem in Linear Rectifiers: Thresholded Exponential Rectified Linear Units 4 Jun 2020 · 0 repositories · arXiv:2006.02797
-
Deep Learning with S-shaped Rectified Linear Activation Units 22 Dec 2015 · 1 repository · arXiv:1512.07030
Tasks archive 2025-07-28
1 task the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.
| Task | Papers |
|---|---|
| Deep Learning | 1 |
Usage over time archive 2025-07-28
Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).
Categories archive 2025-07-28
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections