Mapping Hebbian Learning Rules to Coupling Resistances for Oscillatory Neural Networks

Oscillatory Neural Network (ONN) is an emerging neuromorphic architecture with oscillators representing neurons and information encoded in oscillator's phase relations. In an ONN, oscillators are coupled with electrical elements to define the network's weights and achieve massive parallel...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Corentin Delacour, Aida Todri-Sanial
Formato:	article
Lenguaje:	EN
Publicado:	Frontiers Media S.A. 2021
Materias:	oscillatory neural network VO2 device coupled relaxation oscillators dynamics Hopfield Neural Network Hebbian learning rule pattern recognition Neurosciences. Biological psychiatry. Neuropsychiatry RC321-571
Acceso en línea:	https://doaj.org/article/e8451ed60ddf49f18fff1a097e548f18
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:e8451ed60ddf49f18fff1a097e548f18
record_format	dspace
spelling	oai:doaj.org-article:e8451ed60ddf49f18fff1a097e548f182021-11-08T07:57:26ZMapping Hebbian Learning Rules to Coupling Resistances for Oscillatory Neural Networks1662-453X10.3389/fnins.2021.694549https://doaj.org/article/e8451ed60ddf49f18fff1a097e548f182021-11-01T00:00:00Zhttps://www.frontiersin.org/articles/10.3389/fnins.2021.694549/fullhttps://doaj.org/toc/1662-453XOscillatory Neural Network (ONN) is an emerging neuromorphic architecture with oscillators representing neurons and information encoded in oscillator's phase relations. In an ONN, oscillators are coupled with electrical elements to define the network's weights and achieve massive parallel computation. As the weights preserve the network functionality, mapping weights to coupling elements plays a crucial role in ONN performance. In this work, we investigate relaxation oscillators based on VO2 material, and we propose a methodology to map Hebbian coefficients to ONN coupling resistances, allowing a large-scale ONN design. We develop an analytical framework to map weight coefficients into coupling resistor values to analyze ONN architecture performance. We report on an ONN with 60 fully-connected oscillators that perform pattern recognition as a Hopfield Neural Network.Corentin DelacourAida Todri-SanialFrontiers Media S.A.articleoscillatory neural networkVO2 devicecoupled relaxation oscillators dynamicsHopfield Neural NetworkHebbian learning rulepattern recognitionNeurosciences. Biological psychiatry. NeuropsychiatryRC321-571ENFrontiers in Neuroscience, Vol 15 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	oscillatory neural network VO2 device coupled relaxation oscillators dynamics Hopfield Neural Network Hebbian learning rule pattern recognition Neurosciences. Biological psychiatry. Neuropsychiatry RC321-571
spellingShingle	oscillatory neural network VO2 device coupled relaxation oscillators dynamics Hopfield Neural Network Hebbian learning rule pattern recognition Neurosciences. Biological psychiatry. Neuropsychiatry RC321-571 Corentin Delacour Aida Todri-Sanial Mapping Hebbian Learning Rules to Coupling Resistances for Oscillatory Neural Networks
description	Oscillatory Neural Network (ONN) is an emerging neuromorphic architecture with oscillators representing neurons and information encoded in oscillator's phase relations. In an ONN, oscillators are coupled with electrical elements to define the network's weights and achieve massive parallel computation. As the weights preserve the network functionality, mapping weights to coupling elements plays a crucial role in ONN performance. In this work, we investigate relaxation oscillators based on VO2 material, and we propose a methodology to map Hebbian coefficients to ONN coupling resistances, allowing a large-scale ONN design. We develop an analytical framework to map weight coefficients into coupling resistor values to analyze ONN architecture performance. We report on an ONN with 60 fully-connected oscillators that perform pattern recognition as a Hopfield Neural Network.
format	article
author	Corentin Delacour Aida Todri-Sanial
author_facet	Corentin Delacour Aida Todri-Sanial
author_sort	Corentin Delacour
title	Mapping Hebbian Learning Rules to Coupling Resistances for Oscillatory Neural Networks
title_short	Mapping Hebbian Learning Rules to Coupling Resistances for Oscillatory Neural Networks
title_full	Mapping Hebbian Learning Rules to Coupling Resistances for Oscillatory Neural Networks
title_fullStr	Mapping Hebbian Learning Rules to Coupling Resistances for Oscillatory Neural Networks
title_full_unstemmed	Mapping Hebbian Learning Rules to Coupling Resistances for Oscillatory Neural Networks
title_sort	mapping hebbian learning rules to coupling resistances for oscillatory neural networks
publisher	Frontiers Media S.A.
publishDate	2021
url	https://doaj.org/article/e8451ed60ddf49f18fff1a097e548f18
work_keys_str_mv	AT corentindelacour mappinghebbianlearningrulestocouplingresistancesforoscillatoryneuralnetworks AT aidatodrisanial mappinghebbianlearningrulestocouplingresistancesforoscillatoryneuralnetworks
_version_	1718442862457126912

Mapping Hebbian Learning Rules to Coupling Resistances for Oscillatory Neural Networks

Ejemplares similares