Show simple item record

dc.contributor.authorMadan, Spandan
dc.contributor.authorHenry, Timothy
dc.contributor.authorDozier, Jamell
dc.contributor.authorHo, Helen
dc.contributor.authorBhandari, Nishchal
dc.contributor.authorSasaki, Tomotake
dc.contributor.authorDurand, Frédo
dc.contributor.authorPfister, Hanspeter
dc.contributor.authorBoix, Xavier
dc.date.accessioned2022-06-17T18:38:56Z
dc.date.available2022-06-17T18:38:56Z
dc.date.issued2022-02
dc.identifier.urihttps://hdl.handle.net/1721.1/143479
dc.language.isoen
dc.publisherSpringer Science and Business Media LLCen_US
dc.relation.isversionof10.1038/s42256-021-00437-5en_US
dc.rightsCreative Commons Attribution-Noncommercial-Share Alikeen_US
dc.rights.urihttp://creativecommons.org/licenses/by-nc-sa/4.0/en_US
dc.sourcearXiven_US
dc.titleWhen and how convolutional neural networks generalize to out-of-distribution category–viewpoint combinationsen_US
dc.typeArticleen_US
dc.identifier.citationMadan, Spandan, Henry, Timothy, Dozier, Jamell, Ho, Helen, Bhandari, Nishchal et al. 2022. "When and how convolutional neural networks generalize to out-of-distribution category–viewpoint combinations." Nature Machine Intelligence, 4 (2).
dc.contributor.departmentCenter for Brains, Minds, and Machines
dc.contributor.departmentMassachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory
dc.relation.journalNature Machine Intelligenceen_US
dc.eprint.versionOriginal manuscripten_US
dc.type.urihttp://purl.org/eprint/type/JournalArticleen_US
eprint.statushttp://purl.org/eprint/status/NonPeerRevieweden_US
dc.date.updated2022-06-17T18:05:17Z
dspace.orderedauthorsMadan, S; Henry, T; Dozier, J; Ho, H; Bhandari, N; Sasaki, T; Durand, F; Pfister, H; Boix, Xen_US
dspace.date.submission2022-06-17T18:05:45Z
mit.journal.volume4en_US
mit.journal.issue2en_US
mit.licenseOPEN_ACCESS_POLICY
mit.metadata.statusAuthority Work and Publication Information Neededen_US


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record