Deep neural networks using a single neuron: folded-in-time architecture using feedback-modulated delay loops

Development of deep neural networks benefits from new approaches and perspectives. Stelzer et al. propose to fold a deep neural network of arbitrary size into a single neuron with multiple time-delayed feedback loops which is also of relevance for new hardware implementations and applications.

Guardado en:

Detalles Bibliográficos
Autores principales:	Florian Stelzer, André Röhm, Raul Vicente, Ingo Fischer, Serhiy Yanchuk
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2021
Materias:	Science Q
Acceso en línea:	https://doaj.org/article/a30698a825bc4477addc0a41c91fd055
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:a30698a825bc4477addc0a41c91fd055
record_format	dspace
spelling	oai:doaj.org-article:a30698a825bc4477addc0a41c91fd0552021-12-02T15:09:09ZDeep neural networks using a single neuron: folded-in-time architecture using feedback-modulated delay loops10.1038/s41467-021-25427-42041-1723https://doaj.org/article/a30698a825bc4477addc0a41c91fd0552021-08-01T00:00:00Zhttps://doi.org/10.1038/s41467-021-25427-4https://doaj.org/toc/2041-1723Development of deep neural networks benefits from new approaches and perspectives. Stelzer et al. propose to fold a deep neural network of arbitrary size into a single neuron with multiple time-delayed feedback loops which is also of relevance for new hardware implementations and applications.Florian StelzerAndré RöhmRaul VicenteIngo FischerSerhiy YanchukNature PortfolioarticleScienceQENNature Communications, Vol 12, Iss 1, Pp 1-10 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Science Q
spellingShingle	Science Q Florian Stelzer André Röhm Raul Vicente Ingo Fischer Serhiy Yanchuk Deep neural networks using a single neuron: folded-in-time architecture using feedback-modulated delay loops
description	Development of deep neural networks benefits from new approaches and perspectives. Stelzer et al. propose to fold a deep neural network of arbitrary size into a single neuron with multiple time-delayed feedback loops which is also of relevance for new hardware implementations and applications.
format	article
author	Florian Stelzer André Röhm Raul Vicente Ingo Fischer Serhiy Yanchuk
author_facet	Florian Stelzer André Röhm Raul Vicente Ingo Fischer Serhiy Yanchuk
author_sort	Florian Stelzer
title	Deep neural networks using a single neuron: folded-in-time architecture using feedback-modulated delay loops
title_short	Deep neural networks using a single neuron: folded-in-time architecture using feedback-modulated delay loops
title_full	Deep neural networks using a single neuron: folded-in-time architecture using feedback-modulated delay loops
title_fullStr	Deep neural networks using a single neuron: folded-in-time architecture using feedback-modulated delay loops
title_full_unstemmed	Deep neural networks using a single neuron: folded-in-time architecture using feedback-modulated delay loops
title_sort	deep neural networks using a single neuron: folded-in-time architecture using feedback-modulated delay loops
publisher	Nature Portfolio
publishDate	2021
url	https://doaj.org/article/a30698a825bc4477addc0a41c91fd055
work_keys_str_mv	AT florianstelzer deepneuralnetworksusingasingleneuronfoldedintimearchitectureusingfeedbackmodulateddelayloops AT andrerohm deepneuralnetworksusingasingleneuronfoldedintimearchitectureusingfeedbackmodulateddelayloops AT raulvicente deepneuralnetworksusingasingleneuronfoldedintimearchitectureusingfeedbackmodulateddelayloops AT ingofischer deepneuralnetworksusingasingleneuronfoldedintimearchitectureusingfeedbackmodulateddelayloops AT serhiyyanchuk deepneuralnetworksusingasingleneuronfoldedintimearchitectureusingfeedbackmodulateddelayloops
_version_	1718387892845281280

Deep neural networks using a single neuron: folded-in-time architecture using feedback-modulated delay loops

Ejemplares similares