[source]

Hyperbolic Tangent#

An S-shaped function that squeezes the input value into an output space between -1 and 1. Hyperbolic Tangent (or tanh) has the advantage of being zero centered, however is known to saturate with highly positive or negative input values which can slow down training if the activations become too intense.

Parameters#

This activation Function does not have any parameters.

Example#

use Rubix\ML\NeuralNet\ActivationFunctions\HyperbolicTangent;

$activationFunction = new HyperbolicTangent();