Random synaptic feedback weights support error backpropagation for deep learning

Multi-layered neural architectures that implement learning require elaborate mechanisms for symmetric backpropagation of errors that are biologically implausible. Here the authors propose a simple resolution to this problem of blame assignment that works even with feedback using random synaptic weig...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Timothy P. Lillicrap, Daniel Cownden, Douglas B. Tweed, Colin J. Akerman
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2016
Materias:	Science Q
Acceso en línea:	https://doaj.org/article/7c2d8359409f40dc8a188044a42e7c68
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:7c2d8359409f40dc8a188044a42e7c68
record_format	dspace
spelling	oai:doaj.org-article:7c2d8359409f40dc8a188044a42e7c682021-12-02T14:39:29ZRandom synaptic feedback weights support error backpropagation for deep learning10.1038/ncomms132762041-1723https://doaj.org/article/7c2d8359409f40dc8a188044a42e7c682016-11-01T00:00:00Zhttps://doi.org/10.1038/ncomms13276https://doaj.org/toc/2041-1723Multi-layered neural architectures that implement learning require elaborate mechanisms for symmetric backpropagation of errors that are biologically implausible. Here the authors propose a simple resolution to this problem of blame assignment that works even with feedback using random synaptic weights.Timothy P. LillicrapDaniel CowndenDouglas B. TweedColin J. AkermanNature PortfolioarticleScienceQENNature Communications, Vol 7, Iss 1, Pp 1-10 (2016)
institution	DOAJ
collection	DOAJ
language	EN
topic	Science Q
spellingShingle	Science Q Timothy P. Lillicrap Daniel Cownden Douglas B. Tweed Colin J. Akerman Random synaptic feedback weights support error backpropagation for deep learning
description	Multi-layered neural architectures that implement learning require elaborate mechanisms for symmetric backpropagation of errors that are biologically implausible. Here the authors propose a simple resolution to this problem of blame assignment that works even with feedback using random synaptic weights.
format	article
author	Timothy P. Lillicrap Daniel Cownden Douglas B. Tweed Colin J. Akerman
author_facet	Timothy P. Lillicrap Daniel Cownden Douglas B. Tweed Colin J. Akerman
author_sort	Timothy P. Lillicrap
title	Random synaptic feedback weights support error backpropagation for deep learning
title_short	Random synaptic feedback weights support error backpropagation for deep learning
title_full	Random synaptic feedback weights support error backpropagation for deep learning
title_fullStr	Random synaptic feedback weights support error backpropagation for deep learning
title_full_unstemmed	Random synaptic feedback weights support error backpropagation for deep learning
title_sort	random synaptic feedback weights support error backpropagation for deep learning
publisher	Nature Portfolio
publishDate	2016
url	https://doaj.org/article/7c2d8359409f40dc8a188044a42e7c68
work_keys_str_mv	AT timothyplillicrap randomsynapticfeedbackweightssupporterrorbackpropagationfordeeplearning AT danielcownden randomsynapticfeedbackweightssupporterrorbackpropagationfordeeplearning AT douglasbtweed randomsynapticfeedbackweightssupporterrorbackpropagationfordeeplearning AT colinjakerman randomsynapticfeedbackweightssupporterrorbackpropagationfordeeplearning
_version_	1718390601013002240

Random synaptic feedback weights support error backpropagation for deep learning

Ejemplares similares