The Eighty Five Percent Rule for optimal learning

Is there an optimum difficulty level for training? In this paper, the authors show that for the widely-used class of stochastic gradient-descent based learning algorithms, learning is fastest when the accuracy during training is 85%.

Guardado en:

Detalles Bibliográficos
Autores principales:	Robert C. Wilson, Amitai Shenhav, Mark Straccia, Jonathan D. Cohen
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2019
Materias:	Science Q
Acceso en línea:	https://doaj.org/article/d1aeacdf1f304a25962f05454cebb437
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:d1aeacdf1f304a25962f05454cebb437
record_format	dspace
spelling	oai:doaj.org-article:d1aeacdf1f304a25962f05454cebb4372021-12-02T15:36:06ZThe Eighty Five Percent Rule for optimal learning10.1038/s41467-019-12552-42041-1723https://doaj.org/article/d1aeacdf1f304a25962f05454cebb4372019-11-01T00:00:00Zhttps://doi.org/10.1038/s41467-019-12552-4https://doaj.org/toc/2041-1723Is there an optimum difficulty level for training? In this paper, the authors show that for the widely-used class of stochastic gradient-descent based learning algorithms, learning is fastest when the accuracy during training is 85%.Robert C. WilsonAmitai ShenhavMark StracciaJonathan D. CohenNature PortfolioarticleScienceQENNature Communications, Vol 10, Iss 1, Pp 1-9 (2019)
institution	DOAJ
collection	DOAJ
language	EN
topic	Science Q
spellingShingle	Science Q Robert C. Wilson Amitai Shenhav Mark Straccia Jonathan D. Cohen The Eighty Five Percent Rule for optimal learning
description	Is there an optimum difficulty level for training? In this paper, the authors show that for the widely-used class of stochastic gradient-descent based learning algorithms, learning is fastest when the accuracy during training is 85%.
format	article
author	Robert C. Wilson Amitai Shenhav Mark Straccia Jonathan D. Cohen
author_facet	Robert C. Wilson Amitai Shenhav Mark Straccia Jonathan D. Cohen
author_sort	Robert C. Wilson
title	The Eighty Five Percent Rule for optimal learning
title_short	The Eighty Five Percent Rule for optimal learning
title_full	The Eighty Five Percent Rule for optimal learning
title_fullStr	The Eighty Five Percent Rule for optimal learning
title_full_unstemmed	The Eighty Five Percent Rule for optimal learning
title_sort	eighty five percent rule for optimal learning
publisher	Nature Portfolio
publishDate	2019
url	https://doaj.org/article/d1aeacdf1f304a25962f05454cebb437
work_keys_str_mv	AT robertcwilson theeightyfivepercentruleforoptimallearning AT amitaishenhav theeightyfivepercentruleforoptimallearning AT markstraccia theeightyfivepercentruleforoptimallearning AT jonathandcohen theeightyfivepercentruleforoptimallearning AT robertcwilson eightyfivepercentruleforoptimallearning AT amitaishenhav eightyfivepercentruleforoptimallearning AT markstraccia eightyfivepercentruleforoptimallearning AT jonathandcohen eightyfivepercentruleforoptimallearning
_version_	1718386383589998592

The Eighty Five Percent Rule for optimal learning

Ejemplares similares