Skip to main content

Research Repository

Advanced Search

Are artificial dendrites useful in neuro-evolution?

Bull, Larry

Are artificial dendrites useful in neuro-evolution? Thumbnail


Authors

Lawrence Bull Larry.Bull@uwe.ac.uk
School Director (Research & Enterprise) and Professor



Abstract

The significant role of dendritic processing within neuronal networks has become increasingly clear. This letter explores the effects of including a simple dendrite-inspired mechanism into neuro-evolution. The phenomenon of separate dendrite activation thresholds on connections is allowed to emerge under an evolutionary process. It is shown how such processing can be positively selected for, particularly for connections between the hidden and output layers, and increases performance.

Journal Article Type Article
Acceptance Date Apr 15, 2021
Online Publication Date May 2, 2021
Publication Date 2022-08
Deposit Date Apr 21, 2021
Publicly Available Date Jun 3, 2021
Journal Artificial Life
Print ISSN 1064-5462
Electronic ISSN 1530-9185
Publisher Massachusetts Institute of Technology Press (MIT Press)
Peer Reviewed Peer Reviewed
Volume 27
Issue 2
Article Number 00338
Pages 75-79
DOI https://doi.org/10.1162/artl_a_00338
Keywords connectivity; multilayer perceptron; synapse; regression
Public URL https://uwe-repository.worktribe.com/output/7278194
Publisher URL https://direct.mit.edu/artl/article/27/2/75/102754/Are-Artificial-Dendrites-Useful-in-Neuro-Evolution?searchresult=1

Files

Are artificial dendrites useful in neuroevolution? (553 Kb)
PDF

Licence
http://www.rioxx.net/licenses/all-rights-reserved

Publisher Licence URL
http://www.rioxx.net/licenses/all-rights-reserved

Copyright Statement
This is the author's accepted manuscript of the article 'Are Artificial Dendrites Useful in Neuro-Evolution?' Published in 'Artificial Life' (2021) 27 (2): 75–79. The final published version is available here: https://direct.mit.edu/artl/article/27/2/75/102754/Are-Artificial-Dendrites-Useful-in-Neuro-Evolution?searchresult=1

DOI: https://doi.org/10.1162/artl_a_00338

[Citation] © 2021 Massachusetts Institute of Technology






You might also like



Downloadable Citations