Show simple item record

dc.contributor.authorWilson, Robert C
dc.contributor.authorShenhav, Amitai
dc.contributor.authorStraccia, Mark
dc.contributor.authorCohen, Jonathan D
dc.date.accessioned2019-12-06T02:49:11Z
dc.date.available2019-12-06T02:49:11Z
dc.date.issued2019-11-05
dc.identifier.citationWilson, R.C., Shenhav, A., Straccia, M. et al. The Eighty Five Percent Rule for optimal learning. Nat Commun 10, 4646 (2019) doi:10.1038/s41467-019-12552-4en_US
dc.identifier.issn2041-1723
dc.identifier.pmid31690723
dc.identifier.doi10.1038/s41467-019-12552-4
dc.identifier.urihttp://hdl.handle.net/10150/636293
dc.description.abstractResearchers and educators have long wrestled with the question of how best to teach their clients be they humans, non-human animals or machines. Here, we examine the role of a single variable, the difficulty of training, on the rate of learning. In many situations we find that there is a sweet spot in which training is neither too easy nor too hard, and where learning progresses most quickly. We derive conditions for this sweet spot for a broad class of learning algorithms in the context of binary classification tasks. For all of these stochastic gradient-descent based learning algorithms, we find that the optimal error rate for training is around 15.87% or, conversely, that the optimal training accuracy is about 85%. We demonstrate the efficacy of this ‘Eighty Five Percent Rule’ for artificial neural networks used in AI and biologically plausible neural networks thought to describe animal learning.en_US
dc.description.sponsorshipJohn Templeton Foundation; Center of Biomedical Research Excellence grant from National Institute of General Medical Sciences [P20GM103645]; United States Department of Health & Human Services National Institutes of Health (NIH) - National Institute on Aging (NIA) [R56 AG061888]en_US
dc.language.isoenen_US
dc.publisherNATURE PUBLISHING GROUPen_US
dc.rightsCopyright © The Author(s) 2019. Open Access This article is licensed under a Creative Commons Attribution 4.0 International License. To view a copy of this license, visit http://creativecommons.org/ licenses/by/4.0/.en_US
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/
dc.titleThe Eighty Five Percent Rule for optimal learningen_US
dc.typeArticleen_US
dc.contributor.departmentUniv Arizona, Dept Psycholen_US
dc.contributor.departmentUniv Arizona, Cognit Sci Programen_US
dc.identifier.journalNATURE COMMUNICATIONSen_US
dc.description.noteOpen access journalen_US
dc.description.collectioninformationThis item from the UA Faculty Publications collection is made available by the University of Arizona with support from the University of Arizona Libraries. If you have questions, please contact us at repository@u.library.arizona.edu.en_US
dc.eprint.versionFinal published versionen_US
dc.source.journaltitleNature communications
refterms.dateFOA2019-12-06T02:49:11Z


Files in this item

Thumbnail
Name:
s41467-019-12552-4.pdf
Size:
842.1Kb
Format:
PDF
Description:
Final Published Version

This item appears in the following Collection(s)

Show simple item record

Copyright © The Author(s) 2019. Open Access This article is licensed under a Creative Commons Attribution 4.0 International License. To view a copy of this license, visit http://creativecommons.org/ licenses/by/4.0/.
Except where otherwise noted, this item's license is described as Copyright © The Author(s) 2019. Open Access This article is licensed under a Creative Commons Attribution 4.0 International License. To view a copy of this license, visit http://creativecommons.org/ licenses/by/4.0/.