Skip to main content

Technical perspective: Why don't today's deep nets overfit to their training data?

Author(s): Arora, Sanjeev

Download
To refer to this page use: http://arks.princeton.edu/ark:/88435/pr10c2q
Full metadata record
DC FieldValueLanguage
dc.contributor.authorArora, Sanjeev-
dc.date.accessioned2021-10-08T19:50:39Z-
dc.date.available2021-10-08T19:50:39Z-
dc.date.issued2021en_US
dc.identifier.citationArora, Sanjeev. "Technical perspective: Why don't today's deep nets overfit to their training data?." Communications of the ACM 64, no. 3 (2021): pp. 106. doi:10.1145/3446773en_US
dc.identifier.issn0001-0782-
dc.identifier.urihttp://arks.princeton.edu/ark:/88435/pr10c2q-
dc.description.abstractTHE FOLLOWING ARTICLE by Zhang et al. is well-known for having highlighted that widespread success of deep learn- ing in artificial intelligence brings with it a fundamental new theoretical challenge, specifically: Why don’t to- day’s deep nets overfit to training data? This question has come to animate the theory of deep learning.en_US
dc.format.extent106en_US
dc.language.isoen_USen_US
dc.relation.ispartofCommunications of the ACMen_US
dc.rightsFinal published version. Article is made available in OAR by the publisher's permission or policy.en_US
dc.titleTechnical perspective: Why don't today's deep nets overfit to their training data?en_US
dc.typeJournal Articleen_US
dc.identifier.doi10.1145/3446773-
pu.type.symplectichttp://www.symplectic.co.uk/publications/atom-terms/1.0/journal-articleen_US

Files in This Item:
File Description SizeFormat 
DeepNetNoOverfit.pdf437.12 kBAdobe PDFView/Download


Items in OAR@Princeton are protected by copyright, with all rights reserved, unless otherwise indicated.