Biologically-inspired neuronal adaptation improves learning in neural networks.
Bio-plausible neural networks
contrastive Hebbian learning
equilibrium propagation
neuronal adaptation
Journal
Communicative & integrative biology
ISSN: 1942-0889
Titre abrégé: Commun Integr Biol
Pays: United States
ID NLM: 101478473
Informations de publication
Date de publication:
2023
2023
Historique:
entrez:
23
1
2023
pubmed:
24
1
2023
medline:
24
1
2023
Statut:
epublish
Résumé
Since humans still outperform artificial neural networks on many tasks, drawing inspiration from the brain may help to improve current machine learning algorithms. Contrastive Hebbian learning (CHL) and equilibrium propagation (EP) are biologically plausible algorithms that update weights using only local information (without explicitly calculating gradients) and still achieve performance comparable to conventional backpropagation. In this study, we augmented CHL and EP with
Identifiants
pubmed: 36685291
doi: 10.1080/19420889.2022.2163131
pii: 2163131
pmc: PMC9851208
doi:
Types de publication
Journal Article
Langues
eng
Pagination
2163131Informations de copyright
© 2023 The Author(s). Published by Informa UK Limited, trading as Taylor & Francis Group.
Déclaration de conflit d'intérêts
No potential conflict of interest was reported by the authors.
Références
Front Comput Neurosci. 2022 Aug 23;16:980613
pubmed: 36082305
J Neurosci Methods. 2005 May 15;144(1):53-61
pubmed: 15848239
Nature. 1989 Jan 12;337(6203):129-32
pubmed: 2911347
Front Neurosci. 2021 Feb 18;15:633674
pubmed: 33679315
Front Syst Neurosci. 2022 Jan 11;15:767461
pubmed: 35087383
Neural Comput. 2003 Feb;15(2):441-54
pubmed: 12590814
Phys Rev Lett. 1987 Nov 9;59(19):2229-2232
pubmed: 10035458
Neural Comput. 2019 Feb;31(2):312-329
pubmed: 30576611
Nat Neurosci. 1999 Jun;2(6):521-7
pubmed: 10448216
Nat Commun. 2016 Nov 08;7:13276
pubmed: 27824044
J Neurosci Methods. 2004 Jun 15;136(1):77-85
pubmed: 15126048
Curr Biol. 2021 Feb 8;31(3):R110-R116
pubmed: 33561404
Neural Comput. 1991 Winter;3(4):526-545
pubmed: 31167332
Nat Mach Intell. 2022 Jan;4(1):62-72
pubmed: 35814496
J Neurosci. 2000 Jan 1;20(1):470-84
pubmed: 10627623
Neuroinformatics. 2004;2(3):361-6
pubmed: 15365197
Front Comput Neurosci. 2014 Sep 18;8:116
pubmed: 25278872
J Vis Exp. 2011 Oct 19;(56):
pubmed: 22042361
PLoS Comput Biol. 2014 Apr 10;10(4):e1003560
pubmed: 24722397
Neuroreport. 2012 Mar 7;23(4):240-5
pubmed: 22314684
Neuron. 2016 Oct 19;92(2):298-315
pubmed: 27764664
Cogn Neuropsychol. 2005 Jan 1;22(3):276-91
pubmed: 21038250
Nature. 2016 Jan 28;529(7587):484-9
pubmed: 26819042
J Comput Neurosci. 2003 May-Jun;14(3):271-82
pubmed: 12766428
PLoS Biol. 2019 Nov 21;17(11):e3000516
pubmed: 31751328
J Neurosci. 2004 Mar 31;24(13):3295-303
pubmed: 15056709
J Physiol. 1963 Oct;168:911-31
pubmed: 14072865
Front Comput Neurosci. 2017 May 04;11:24
pubmed: 28522969
Nature. 2015 Feb 26;518(7540):529-33
pubmed: 25719670
Hippocampus. 2004;14(5):539-56
pubmed: 15301433
Nat Rev Neurosci. 2020 Jun;21(6):335-346
pubmed: 32303713