Improving the performance of mutation-based evolving artificial neural networks with self-adaptive mutations.

Improving the performance of mutation-based evolving artificial neural networks with self-adaptive mutations.

Neuroevolution is a promising approach for designing artificial neural networks using an evolutionary algorithm. Unlike recent trending methods that rely on gradient-based algorithms, neuroevolution can simultaneously evolve the topology and weights of neural networks. In neuroevolution with topolog...

Full description

Bibliographic Details
Main Authors: Motoaki Hiraga, Masahiro Komura, Akiharu Miyamoto, Daichi Morimoto, Kazuhiro Ohkura
Format: Article
Language:English
Published: Public Library of Science (PLoS) 2024-01-01
Series:PLoS ONE
Online Access:https://doi.org/10.1371/journal.pone.0307084

Internet

https://doi.org/10.1371/journal.pone.0307084

Similar Items