Cargando…

Learning to Generate Sequences with Combination of Hebbian and Non-hebbian Plasticity in Recurrent Spiking Neural Networks

Synaptic Plasticity, the foundation for learning and memory formation in the human brain, manifests in various forms. Here, we combine the standard spike timing correlation based Hebbian plasticity with a non-Hebbian synaptic decay mechanism for training a recurrent spiking neural model to generate...

Descripción completa

Detalles Bibliográficos
Autores principales: Panda, Priyadarshini, Roy, Kaushik
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Frontiers Media S.A. 2017
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5733011/
https://www.ncbi.nlm.nih.gov/pubmed/29311774
http://dx.doi.org/10.3389/fnins.2017.00693
_version_ 1783286818094972928
author Panda, Priyadarshini
Roy, Kaushik
author_facet Panda, Priyadarshini
Roy, Kaushik
author_sort Panda, Priyadarshini
collection PubMed
description Synaptic Plasticity, the foundation for learning and memory formation in the human brain, manifests in various forms. Here, we combine the standard spike timing correlation based Hebbian plasticity with a non-Hebbian synaptic decay mechanism for training a recurrent spiking neural model to generate sequences. We show that inclusion of the adaptive decay of synaptic weights with standard STDP helps learn stable contextual dependencies between temporal sequences, while reducing the strong attractor states that emerge in recurrent models due to feedback loops. Furthermore, we show that the combined learning scheme suppresses the chaotic activity in the recurrent model substantially, thereby enhancing its' ability to generate sequences consistently even in the presence of perturbations.
format Online
Article
Text
id pubmed-5733011
institution National Center for Biotechnology Information
language English
publishDate 2017
publisher Frontiers Media S.A.
record_format MEDLINE/PubMed
spelling pubmed-57330112018-01-08 Learning to Generate Sequences with Combination of Hebbian and Non-hebbian Plasticity in Recurrent Spiking Neural Networks Panda, Priyadarshini Roy, Kaushik Front Neurosci Neuroscience Synaptic Plasticity, the foundation for learning and memory formation in the human brain, manifests in various forms. Here, we combine the standard spike timing correlation based Hebbian plasticity with a non-Hebbian synaptic decay mechanism for training a recurrent spiking neural model to generate sequences. We show that inclusion of the adaptive decay of synaptic weights with standard STDP helps learn stable contextual dependencies between temporal sequences, while reducing the strong attractor states that emerge in recurrent models due to feedback loops. Furthermore, we show that the combined learning scheme suppresses the chaotic activity in the recurrent model substantially, thereby enhancing its' ability to generate sequences consistently even in the presence of perturbations. Frontiers Media S.A. 2017-12-12 /pmc/articles/PMC5733011/ /pubmed/29311774 http://dx.doi.org/10.3389/fnins.2017.00693 Text en Copyright © 2017 Panda and Roy. http://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) or licensor 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
Panda, Priyadarshini
Roy, Kaushik
Learning to Generate Sequences with Combination of Hebbian and Non-hebbian Plasticity in Recurrent Spiking Neural Networks
title Learning to Generate Sequences with Combination of Hebbian and Non-hebbian Plasticity in Recurrent Spiking Neural Networks
title_full Learning to Generate Sequences with Combination of Hebbian and Non-hebbian Plasticity in Recurrent Spiking Neural Networks
title_fullStr Learning to Generate Sequences with Combination of Hebbian and Non-hebbian Plasticity in Recurrent Spiking Neural Networks
title_full_unstemmed Learning to Generate Sequences with Combination of Hebbian and Non-hebbian Plasticity in Recurrent Spiking Neural Networks
title_short Learning to Generate Sequences with Combination of Hebbian and Non-hebbian Plasticity in Recurrent Spiking Neural Networks
title_sort learning to generate sequences with combination of hebbian and non-hebbian plasticity in recurrent spiking neural networks
topic Neuroscience
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5733011/
https://www.ncbi.nlm.nih.gov/pubmed/29311774
http://dx.doi.org/10.3389/fnins.2017.00693
work_keys_str_mv AT pandapriyadarshini learningtogeneratesequenceswithcombinationofhebbianandnonhebbianplasticityinrecurrentspikingneuralnetworks
AT roykaushik learningtogeneratesequenceswithcombinationofhebbianandnonhebbianplasticityinrecurrentspikingneuralnetworks