A solution to the learning dilemma for recurrent networks of spiking neurons

A solution to the learning dilemma for recurrent networks of spiking neurons

Bellec et al. present a mathematically founded approximation for gradient descent training of recurrent neural networks without backwards propagation in time. This enables biologically plausible training of spike-based neural network models with working memory and supports on-chip training of neurom...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Guillaume Bellec, Franz Scherr, Anand Subramoney, Elias Hajek, Darjan Salaj, Robert Legenstein, Wolfgang Maass
Formato: article
Lenguaje:EN
Publicado: Nature Portfolio 2020
Materias:
Science
Q
Acceso en línea:https://doaj.org/article/7910940bc2a3480f8457777933723618
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:7910940bc2a3480f8457777933723618
record_format dspace
spelling oai:doaj.org-article:7910940bc2a3480f84577779337236182021-12-02T17:01:30ZA solution to the learning dilemma for recurrent networks of spiking neurons10.1038/s41467-020-17236-y2041-1723https://doaj.org/article/7910940bc2a3480f84577779337236182020-07-01T00:00:00Zhttps://doi.org/10.1038/s41467-020-17236-yhttps://doaj.org/toc/2041-1723Bellec et al. present a mathematically founded approximation for gradient descent training of recurrent neural networks without backwards propagation in time. This enables biologically plausible training of spike-based neural network models with working memory and supports on-chip training of neuromorphic hardware.Guillaume BellecFranz ScherrAnand SubramoneyElias HajekDarjan SalajRobert LegensteinWolfgang MaassNature PortfolioarticleScienceQENNature Communications, Vol 11, Iss 1, Pp 1-15 (2020)
institution DOAJ
collection DOAJ
language EN
topic Science
Q
spellingShingle Science
Q
Guillaume Bellec
Franz Scherr
Anand Subramoney
Elias Hajek
Darjan Salaj
Robert Legenstein
Wolfgang Maass
A solution to the learning dilemma for recurrent networks of spiking neurons
description Bellec et al. present a mathematically founded approximation for gradient descent training of recurrent neural networks without backwards propagation in time. This enables biologically plausible training of spike-based neural network models with working memory and supports on-chip training of neuromorphic hardware.
format article
author Guillaume Bellec
Franz Scherr
Anand Subramoney
Elias Hajek
Darjan Salaj
Robert Legenstein
Wolfgang Maass
author_facet Guillaume Bellec
Franz Scherr
Anand Subramoney
Elias Hajek
Darjan Salaj
Robert Legenstein
Wolfgang Maass
author_sort Guillaume Bellec
title A solution to the learning dilemma for recurrent networks of spiking neurons
title_short A solution to the learning dilemma for recurrent networks of spiking neurons
title_full A solution to the learning dilemma for recurrent networks of spiking neurons
title_fullStr A solution to the learning dilemma for recurrent networks of spiking neurons
title_full_unstemmed A solution to the learning dilemma for recurrent networks of spiking neurons
title_sort solution to the learning dilemma for recurrent networks of spiking neurons
publisher Nature Portfolio
publishDate 2020
url https://doaj.org/article/7910940bc2a3480f8457777933723618
work_keys_str_mv AT guillaumebellec asolutiontothelearningdilemmaforrecurrentnetworksofspikingneurons
AT franzscherr asolutiontothelearningdilemmaforrecurrentnetworksofspikingneurons
AT anandsubramoney asolutiontothelearningdilemmaforrecurrentnetworksofspikingneurons
AT eliashajek asolutiontothelearningdilemmaforrecurrentnetworksofspikingneurons
AT darjansalaj asolutiontothelearningdilemmaforrecurrentnetworksofspikingneurons
AT robertlegenstein asolutiontothelearningdilemmaforrecurrentnetworksofspikingneurons
AT wolfgangmaass asolutiontothelearningdilemmaforrecurrentnetworksofspikingneurons
AT guillaumebellec solutiontothelearningdilemmaforrecurrentnetworksofspikingneurons
AT franzscherr solutiontothelearningdilemmaforrecurrentnetworksofspikingneurons
AT anandsubramoney solutiontothelearningdilemmaforrecurrentnetworksofspikingneurons
AT eliashajek solutiontothelearningdilemmaforrecurrentnetworksofspikingneurons
AT darjansalaj solutiontothelearningdilemmaforrecurrentnetworksofspikingneurons
AT robertlegenstein solutiontothelearningdilemmaforrecurrentnetworksofspikingneurons
AT wolfgangmaass solutiontothelearningdilemmaforrecurrentnetworksofspikingneurons
_version_ 1718382090791157760

Ejemplares similares