papyri
{ } Raw JSON

bundles / scipy 1.18.0 / scipy / special / _basic / softplus

function

scipy.special._basic:softplus

source: /scipy/special/_basic.py:3474

Signature

def softplus(x, **kwargs)

Summary

Compute the softplus function element-wise.

Extended Summary

The softplus function is defined as: softplus(x) = log(1 + exp(x)). It is a smooth approximation of the rectifier function (ReLU).

Parameters

x : array_like

Input value.

**kwargs

For other keyword-only arguments, see the ufunc docs.

Returns

softplus : ndarray

Logarithm of exp(0) + exp(x).

Examples

from scipy import special
✓
special.softplus(0)
✗
np.float64(0.6931471805599453)

special.softplus([-1, 0, 1])
✗
array([0.31326, 0.69315, 1.31326])

Aliases

  • scipy.special.softplus

Referenced by

This package