Synaptic metaplasticity in binarized neural networks

Deep neural networks usually rapidly forget the previously learned tasks while training new ones. Laborieux et al. propose a method for training binarized neural networks inspired by neuronal metaplasticity that allows to avoid catastrophic forgetting and is relevant for neuromorphic applications.

Guardado en:

Detalles Bibliográficos
Autores principales:	Axel Laborieux, Maxence Ernoult, Tifenn Hirtzlin, Damien Querlioz
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2021
Materias:	Science Q
Acceso en línea:	https://doaj.org/article/e2b90fdc25c546258715984597f47c48
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:e2b90fdc25c546258715984597f47c48
record_format	dspace
spelling	oai:doaj.org-article:e2b90fdc25c546258715984597f47c482021-12-02T15:38:20ZSynaptic metaplasticity in binarized neural networks10.1038/s41467-021-22768-y2041-1723https://doaj.org/article/e2b90fdc25c546258715984597f47c482021-05-01T00:00:00Zhttps://doi.org/10.1038/s41467-021-22768-yhttps://doaj.org/toc/2041-1723Deep neural networks usually rapidly forget the previously learned tasks while training new ones. Laborieux et al. propose a method for training binarized neural networks inspired by neuronal metaplasticity that allows to avoid catastrophic forgetting and is relevant for neuromorphic applications.Axel LaborieuxMaxence ErnoultTifenn HirtzlinDamien QuerliozNature PortfolioarticleScienceQENNature Communications, Vol 12, Iss 1, Pp 1-12 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Science Q
spellingShingle	Science Q Axel Laborieux Maxence Ernoult Tifenn Hirtzlin Damien Querlioz Synaptic metaplasticity in binarized neural networks
description	Deep neural networks usually rapidly forget the previously learned tasks while training new ones. Laborieux et al. propose a method for training binarized neural networks inspired by neuronal metaplasticity that allows to avoid catastrophic forgetting and is relevant for neuromorphic applications.
format	article
author	Axel Laborieux Maxence Ernoult Tifenn Hirtzlin Damien Querlioz
author_facet	Axel Laborieux Maxence Ernoult Tifenn Hirtzlin Damien Querlioz
author_sort	Axel Laborieux
title	Synaptic metaplasticity in binarized neural networks
title_short	Synaptic metaplasticity in binarized neural networks
title_full	Synaptic metaplasticity in binarized neural networks
title_fullStr	Synaptic metaplasticity in binarized neural networks
title_full_unstemmed	Synaptic metaplasticity in binarized neural networks
title_sort	synaptic metaplasticity in binarized neural networks
publisher	Nature Portfolio
publishDate	2021
url	https://doaj.org/article/e2b90fdc25c546258715984597f47c48
work_keys_str_mv	AT axellaborieux synapticmetaplasticityinbinarizedneuralnetworks AT maxenceernoult synapticmetaplasticityinbinarizedneuralnetworks AT tifennhirtzlin synapticmetaplasticityinbinarizedneuralnetworks AT damienquerlioz synapticmetaplasticityinbinarizedneuralnetworks
_version_	1718386205016457216

Synaptic metaplasticity in binarized neural networks

Ejemplares similares