Skip to content

[source]

Softsign#

A smooth sigmoid-shaped function that squashes the input between -1 and 1.

Softsign=x1+|x|

Parameters#

This activation function does not have any parameters.

Example#

use Rubix\ML\NeuralNet\ActivationFunctions\Softsign;

$activationFunction = new Softsign();

References#


  1. X. Glorot et al. (2010). Understanding the Difficulty of Training Deep Feedforward Neural Networks. 


Last update: 2021-03-03