1<span style="float:right;"><a href="https://github.com/RubixML/ML/blob/master/src/NeuralNet/ActivationFunctions/HyperbolicTangent.php">[source]</a></span>
2
3# Hyperbolic Tangent
4An 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.
5
6$$
7{\displaystyle \tanh(x)={\frac {e^{x}-e^{-x}}{e^{x}+e^{-x}}}}
8$$
9
10## Parameters
11This activation function does not have any parameters.
12
13## Example
14```php
15use Rubix\ML\NeuralNet\ActivationFunctions\HyperbolicTangent;
16
17$activationFunction = new HyperbolicTangent();
18```
19