Methods › General › Activation Functions › SERLU

SERLU

1 paper tagged archive 2025-07-28

Introduced by G. Zhang et al. in Effectiveness of Scaled Exponentially-Regularized Linear Units (SERLUs)

archive 2025-07-28 Description, source and code snippet are the archive's method entry.

SERLU, or Scaled Exponentially-Regularized Linear Unit, is a type of activation function. The new function introduces a bump-shaped function in the region of negative input. The bump-shaped function has approximately zero response to large negative input while being able to push the output of SERLU towards zero mean statistically.

SERLU(x)) = λₛₑᵣₗᵤx if x ≥0 SERLU(x)) = λₛₑᵣₗᵤαₛₑᵣₗᵤxeˣ if x < 0

where the two parameters λₛₑᵣₗᵤ > 0 and αₛₑᵣₗᵤ > 0 remain to be specified.

PaperSourceSee Code · mattresnick/Custom-PyTorch-Resources

Papers archive 2025-07-28

1 shown of 1, 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.

Tasks archive 2025-07-28

The archive attaches no task to a paper tagged with this method.

Usage over time archive 2025-07-28

Papers per year tagged with SERLU: 2018 to 2018, peak 1 1 0 2018: 1 paper 2018
Papers per year the archive tags with this method, by the paper's archive date (1 dated). Bars are counts, not a trend claim.

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

Activation Functions

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