Parameterized Exponential Linear Units, or PELU, is an activation function for neural networks. It involves learning a parameterization of ELU in order to learn the proper activation shape at each layer in a CNN.
The PELU has two additional parameters over the ELU:
$$ f\left(x\right) = cx \text{ if } x > 0 $$ $$ f\left(x\right) = \alpha\exp^{\frac{x}{b}} - 1 \text{ if } x \leq 0 $$
Where $a$, $b$, and $c > 0$. Here $c$ causes a change in the slope in the positive quadrant, $b$ controls the scale of the exponential decay, and $\alpha$ controls the saturation in the negative quadrant.
Source: Activation Functions
Source: Parametric Exponential Linear Unit for Deep Convolutional Neural NetworksPaper | Code | Results | Date | Stars |
---|
Task | Papers | Share |
---|---|---|
Atari Games | 1 | 20.00% |
Image Classification | 1 | 20.00% |
Reinforcement Learning (RL) | 1 | 20.00% |
Object Recognition | 1 | 20.00% |
Scene Understanding | 1 | 20.00% |
Component | Type |
|
---|---|---|
🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |