softplus

Contents

softplus#

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

Softplus activation function.

Computes the element-wise function

\[\mathrm{softplus}(x) = \log(1 + e^x)\]
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 non-negative values.

Return type:

Array

Examples

>>> import jax.numpy as jnp
>>> import saiunit.math as sumath
>>> sumath.softplus(jnp.array([-2., 0., 2.]))
Array([0.12692805, 0.6931472 , 2.126928  ], dtype=float32)
Contents