Evolutionary acquisition of neural topologies
id:
evolutionary-acquisition-of-neural-topologies-319-7480076
title:
Evolutionary acquisition of neural topologies
text:
Evolutionary acquisition of neural topologies (EANT/EANT2) is an evolutionary reinforcement learning method that evolves both the topology and weights of artificial neural networks. It is closely related to the works of Angeline et al. and Stanley and Miikkulainen. Like the work of Angeline et al., the method uses a type of parametric mutation that comes from evolution strategies and evolutionary programming, in which adaptive step sizes are used for optimizing the weights of the neural networks
brand slug:
wiki
category slug:
encyclopedia
description:
Method that evolves both the topology and weights of artificial neural networks
original url:
https://en.wikipedia.org/wiki/Evolutionary_acquisition_of_neural_topologies
date created:
date modified:
2022-12-05T12:28:48Z
main entity:
{"identifier":"Q5418685","url":"https://www.wikidata.org/entity/Q5418685"}
image:
fields total:
13
integrity:
14