Skip to content



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.

\[ {\displaystyle ELU = {\begin{cases}\alpha \left(e^{x}-1\right)&{\text{if }}x\leq 0\\x&{\text{if }}x>0\end{cases}}} \]


# 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.


use Rubix\ML\NeuralNet\ActivationFunctions\ELU;

$activationFunction = new ELU(2.5);


  1. D. A. Clevert et al. (2016). Fast and Accurate Deep Network Learning by Exponential Linear Units.