Swish function
id:
swish-function-293-2943996
title:
Swish function
text:
The swish function is a mathematical function defined as follows: where β is either constant or a trainable parameter depending on the model. For β = 1, the function becomes equivalent to the Sigmoid Linear Unit or SiLU, first proposed alongside the GELU in 2016. The SiLU was later rediscovered in 2017 as the Sigmoid-weighted Linear Unit (SiL) function used in reinforcement learning. The SiLU/SiL was then rediscovered as the swish over a year after its initial discovery, originally proposed with
brand slug:
wiki
category slug:
encyclopedia
description:
Mathematical activation function in data analysis
original url:
https://en.wikipedia.org/wiki/Swish_function
date created:
date modified:
2023-07-22T06:04:28Z
main entity:
{"identifier":"Q97358426","url":"https://www.wikidata.org/entity/Q97358426"}
image:
{"content_url":"https://upload.wikimedia.org/wikipedia/commons/1/12/Swish.svg","width":1000,"height":600}
fields total:
13
integrity:
15