Activation Functions

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.

$$ \text{SERLU}\left(x\right)) = \lambda_{serlu}x \text{ if } x \geq 0 $$ $$ \text{SERLU}\left(x\right)) = \lambda_{serlu}\alpha_{serlu}xe^{x} \text{ if } x < 0 $$

where the two parameters $\lambda_{serlu} > 0$ and $\alpha_{serlu} > 0$ remain to be specified.

Source: Effectiveness of Scaled Exponentially-Regularized Linear Units (SERLUs)


Paper Code Results Date Stars


Component Type
🤖 No Components Found You can add them if they exist; e.g. Mask R-CNN uses RoIAlign