celu

Contents

celu#

class brainunit.math.celu(x, alpha=1.0, unit_to_scale=None)#

Continuously-differentiable exponential linear unit activation.

Computes the element-wise function:

\[\begin{split}\mathrm{celu}(x) = \begin{cases} x, & x > 0\\ \alpha \left(\exp(\frac{x}{\alpha}) - 1\right), & x \le 0 \end{cases}\end{split}\]

For more information, see Continuously Differentiable Exponential Linear Units.

Parameters:

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

  • alpha (Array | ndarray | bool | number | bool | int | float | complex) – Scale parameter. Default is 1.0.

  • 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.celu(jnp.array([-2., 0., 2.]))
Array([-0.86466473,  0.        ,  2.        ], dtype=float32)
Contents