ELU#
Exponential Linear Units are a type of rectifier that soften the transition from non-activated to activated using the exponential function. As such, ELU produces smoother gradients than the piecewise linear ReLU function.
Parameters#
# | Name | Default | Type | Description |
---|---|---|---|---|
1 | alpha | 1.0 | float | The value at which leakage will begin to saturate. Ex. alpha = 1.0 means that the output will never be less than -1.0 when inactivated. |
Example#
use Rubix\ML\NeuralNet\ActivationFunctions\ELU;
$activationFunction = new ELU(2.5);
References#
-
D. A. Clevert et al. (2016). Fast and Accurate Deep Network Learning by Exponential Linear Units. ↩