Cargando…

Synergies between Intrinsic and Synaptic Plasticity Based on Information Theoretic Learning

In experimental and theoretical neuroscience, synaptic plasticity has dominated the area of neural plasticity for a very long time. Recently, neuronal intrinsic plasticity (IP) has become a hot topic in this area. IP is sometimes thought to be an information-maximization mechanism. However, it is st...

Descripción completa

Detalles Bibliográficos
Autores principales: Li, Yuke, Li, Chunguang
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Public Library of Science 2013
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC3650036/
https://www.ncbi.nlm.nih.gov/pubmed/23671642
http://dx.doi.org/10.1371/journal.pone.0062894
_version_ 1782269062768754688
author Li, Yuke
Li, Chunguang
author_facet Li, Yuke
Li, Chunguang
author_sort Li, Yuke
collection PubMed
description In experimental and theoretical neuroscience, synaptic plasticity has dominated the area of neural plasticity for a very long time. Recently, neuronal intrinsic plasticity (IP) has become a hot topic in this area. IP is sometimes thought to be an information-maximization mechanism. However, it is still unclear how IP affects the performance of artificial neural networks in supervised learning applications. From an information-theoretical perspective, the error-entropy minimization (MEE) algorithm has newly been proposed as an efficient training method. In this study, we propose a synergistic learning algorithm combining the MEE algorithm as the synaptic plasticity rule and an information-maximization algorithm as the intrinsic plasticity rule. We consider both feedforward and recurrent neural networks and study the interactions between intrinsic and synaptic plasticity. Simulations indicate that the intrinsic plasticity rule can improve the performance of artificial neural networks trained by the MEE algorithm.
format Online
Article
Text
id pubmed-3650036
institution National Center for Biotechnology Information
language English
publishDate 2013
publisher Public Library of Science
record_format MEDLINE/PubMed
spelling pubmed-36500362013-05-13 Synergies between Intrinsic and Synaptic Plasticity Based on Information Theoretic Learning Li, Yuke Li, Chunguang PLoS One Research Article In experimental and theoretical neuroscience, synaptic plasticity has dominated the area of neural plasticity for a very long time. Recently, neuronal intrinsic plasticity (IP) has become a hot topic in this area. IP is sometimes thought to be an information-maximization mechanism. However, it is still unclear how IP affects the performance of artificial neural networks in supervised learning applications. From an information-theoretical perspective, the error-entropy minimization (MEE) algorithm has newly been proposed as an efficient training method. In this study, we propose a synergistic learning algorithm combining the MEE algorithm as the synaptic plasticity rule and an information-maximization algorithm as the intrinsic plasticity rule. We consider both feedforward and recurrent neural networks and study the interactions between intrinsic and synaptic plasticity. Simulations indicate that the intrinsic plasticity rule can improve the performance of artificial neural networks trained by the MEE algorithm. Public Library of Science 2013-05-09 /pmc/articles/PMC3650036/ /pubmed/23671642 http://dx.doi.org/10.1371/journal.pone.0062894 Text en © 2013 Li, Li http://creativecommons.org/licenses/by/4.0/ This is an open-access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are properly credited.
spellingShingle Research Article
Li, Yuke
Li, Chunguang
Synergies between Intrinsic and Synaptic Plasticity Based on Information Theoretic Learning
title Synergies between Intrinsic and Synaptic Plasticity Based on Information Theoretic Learning
title_full Synergies between Intrinsic and Synaptic Plasticity Based on Information Theoretic Learning
title_fullStr Synergies between Intrinsic and Synaptic Plasticity Based on Information Theoretic Learning
title_full_unstemmed Synergies between Intrinsic and Synaptic Plasticity Based on Information Theoretic Learning
title_short Synergies between Intrinsic and Synaptic Plasticity Based on Information Theoretic Learning
title_sort synergies between intrinsic and synaptic plasticity based on information theoretic learning
topic Research Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC3650036/
https://www.ncbi.nlm.nih.gov/pubmed/23671642
http://dx.doi.org/10.1371/journal.pone.0062894
work_keys_str_mv AT liyuke synergiesbetweenintrinsicandsynapticplasticitybasedoninformationtheoreticlearning
AT lichunguang synergiesbetweenintrinsicandsynapticplasticitybasedoninformationtheoreticlearning