Cargando…

Voltage slope guided learning in spiking neural networks

A thorny problem in machine learning is how to extract useful clues related to delayed feedback signals from the clutter of input activity, known as the temporal credit-assignment problem. The aggregate-label learning algorithms make an explicit representation of this problem by training spiking neu...

Descripción completa

Detalles Bibliográficos
Autores principales: Hu, Lvhui, Liao, Xin
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Frontiers Media S.A. 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9685168/
https://www.ncbi.nlm.nih.gov/pubmed/36440266
http://dx.doi.org/10.3389/fnins.2022.1012964
_version_ 1784835443588595712
author Hu, Lvhui
Liao, Xin
author_facet Hu, Lvhui
Liao, Xin
author_sort Hu, Lvhui
collection PubMed
description A thorny problem in machine learning is how to extract useful clues related to delayed feedback signals from the clutter of input activity, known as the temporal credit-assignment problem. The aggregate-label learning algorithms make an explicit representation of this problem by training spiking neurons to assign the aggregate feedback signal to potentially effective clues. However, earlier aggregate-label learning algorithms suffered from inefficiencies due to the large amount of computation, while recent algorithms that have solved this problem may fail to learn due to the inability to find adjustment points. Therefore, we propose a membrane voltage slope guided algorithm (VSG) to further cope with this limitation. Direct dependence on the membrane voltage when finding the key point of weight adjustment makes VSG avoid intensive calculation, but more importantly, the membrane voltage that always exists makes it impossible to lose the adjustment point. Experimental results show that the proposed algorithm can correlate delayed feedback signals with the effective clues embedded in background spiking activity, and also achieves excellent performance on real medical classification datasets and speech classification datasets. The superior performance makes it a meaningful reference for aggregate-label learning on spiking neural networks.
format Online
Article
Text
id pubmed-9685168
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher Frontiers Media S.A.
record_format MEDLINE/PubMed
spelling pubmed-96851682022-11-25 Voltage slope guided learning in spiking neural networks Hu, Lvhui Liao, Xin Front Neurosci Neuroscience A thorny problem in machine learning is how to extract useful clues related to delayed feedback signals from the clutter of input activity, known as the temporal credit-assignment problem. The aggregate-label learning algorithms make an explicit representation of this problem by training spiking neurons to assign the aggregate feedback signal to potentially effective clues. However, earlier aggregate-label learning algorithms suffered from inefficiencies due to the large amount of computation, while recent algorithms that have solved this problem may fail to learn due to the inability to find adjustment points. Therefore, we propose a membrane voltage slope guided algorithm (VSG) to further cope with this limitation. Direct dependence on the membrane voltage when finding the key point of weight adjustment makes VSG avoid intensive calculation, but more importantly, the membrane voltage that always exists makes it impossible to lose the adjustment point. Experimental results show that the proposed algorithm can correlate delayed feedback signals with the effective clues embedded in background spiking activity, and also achieves excellent performance on real medical classification datasets and speech classification datasets. The superior performance makes it a meaningful reference for aggregate-label learning on spiking neural networks. Frontiers Media S.A. 2022-11-10 /pmc/articles/PMC9685168/ /pubmed/36440266 http://dx.doi.org/10.3389/fnins.2022.1012964 Text en Copyright © 2022 Hu and Liao. https://creativecommons.org/licenses/by/4.0/This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
spellingShingle Neuroscience
Hu, Lvhui
Liao, Xin
Voltage slope guided learning in spiking neural networks
title Voltage slope guided learning in spiking neural networks
title_full Voltage slope guided learning in spiking neural networks
title_fullStr Voltage slope guided learning in spiking neural networks
title_full_unstemmed Voltage slope guided learning in spiking neural networks
title_short Voltage slope guided learning in spiking neural networks
title_sort voltage slope guided learning in spiking neural networks
topic Neuroscience
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9685168/
https://www.ncbi.nlm.nih.gov/pubmed/36440266
http://dx.doi.org/10.3389/fnins.2022.1012964
work_keys_str_mv AT hulvhui voltageslopeguidedlearninginspikingneuralnetworks
AT liaoxin voltageslopeguidedlearninginspikingneuralnetworks