selu

Contents

selu#

class saiunit.math.selu(x, unit_to_scale=None)#

Scaled exponential linear unit activation.

Computes the element-wise function:

\[\begin{split}\mathrm{selu}(x) = \lambda \begin{cases} x, & x > 0\\ \alpha e^x - \alpha, & x \le 0 \end{cases}\end{split}\]

where \(\lambda = 1.0507009873554804934193349852946\) and \(\alpha = 1.6732632423543772848170429916717\).

For more information, see Self-Normalizing Neural Networks.

Parameters:

  • x (Quantity | Array | ndarray | bool | number | bool | int | float | complex) – Input array. Must be unitless if a Quantity.

  • unit_to_scale (Unit | None) – Unit used to convert x to a dimensionless number before applying the activation.

Returns:

out – An array with the same shape as x.

Return type:

Array

Examples

>>> import jax.numpy as jnp
>>> import saiunit.math as sumath
>>> sumath.selu(jnp.array([-2., 0., 2.]))
Array([-1.5201665,  0.       ,  2.1014020], dtype=float32)
Contents