Detailed Description

Scaled exponential rectified linear unit.

$\text{SELU}(x) = \begin{cases} s x & x > 0 \\ s \alpha (e^x - 1) & x \leq 0 \end{cases}$

with $\alpha \approx 1.67$ and $s \approx 1.05$ . Note that SELU is equivalent to $s \, \text{ELU}(x;\alpha)$ . See:

Gunter Klambauer, Thomas Unterthiner, Andreas Mayr, and Sepp Hochreiter. "Self-normalizing neural networks." In Advances in Neural Information Processing Systems, pp. 971-980. 2017.

The documentation for this class was generated from the following file:

activations.hpp