Defined in tensorflow/python/keras/

Scaled Exponential Linear Unit (SELU).

SELU is equal to: scale * elu(x, alpha), where alpha and scale are pre-defined constants. The values of alpha and scale are chosen so that the mean and variance of the inputs are preserved between two consecutive layers as long as the weights are initialized correctly (see lecun_normal initialization) and the number of inputs is "large enough" (see references for more information).


  • x: A tensor or variable to compute the activation function for.


The scaled exponential unit activation: `scale * elu(x, alpha)`.


- To be used together with the initialization "lecun_normal".
- To be used together with the dropout variant "AlphaDropout".

References: - Self-Normalizing Neural Networks