SiLU

Contents

SiLU#

class brainstate.nn.SiLU(name=None)#

Applies the Sigmoid Linear Unit (SiLU) function, element-wise.

The SiLU function is also known as the swish function.

\[\text{silu}(x) = x * \sigma(x), \text{where } \sigma(x) \text{ is the logistic sigmoid.}\]

Notes

See Gaussian Error Linear Units (GELUs) where the SiLU (Sigmoid Linear Unit) was originally coined, and see Sigmoid-Weighted Linear Units for Neural Network Function Approximation in Reinforcement Learning and Swish: a Self-Gated Activation Function where the SiLU was experimented with later.

Shape#

  • Input: \((*)\), where \(*\) means any number of dimensions.

  • Output: \((*)\), same shape as the input.

Examples

>>> import brainstate.nn as nn
>>> import brainstate
>>> m = nn.SiLU()
>>> x = brainstate.random.randn(2)
>>> output = m(x)
Contents