On some similarities and differences between deep neural networks and kernel learning machines

Simple item page
dc.contributor.authorPei, Eddie
dc.contributor.authorFokoué, Ernest
dc.coverage.issue1cs
dc.coverage.volume11cs
dc.date.accessioned2022-06-23T12:18:24Z
dc.date.available2022-06-23T12:18:24Z
dc.date.issued2022cs
dc.description.abstractThis paper presents a thorough computational comparison of the predic- tive performances of deep neural networks and kernel learning machines. The work featured here successfully establishes that on both real-life datasets and artificially simulated ones, kernel learning machines tend to be just as good as deep neural net- works, and quite often outperform them predictively. It turns out from the findings of this paper that while deep neural networks might have worked well on tasks for which millions of observations are available, kernel learning machines just happen to be predictively better on a wide variety of tasks with the kind of sample size that one should realistically expect to have in practice.en
dc.formattextcs
dc.format.extent75-106cs
dc.format.mimetypeapplication/pdfen
dc.identifier.citationMathematics for Applications. 2022 vol. 11, č. 1, s. 75-106. ISSN 1805-3629cs
dc.identifier.doi10.13164/ma.2022.07en
dc.identifier.issn1805-3629
dc.identifier.urihttp://hdl.handle.net/11012/207745
dc.language.isoencs
dc.publisherVysoké učení technické v Brně, Fakulta strojního inženýrství, Ústav matematikycs
dc.relation.ispartofMathematics for Applicationsen
dc.relation.urihttp://ma.fme.vutbr.cz/archiv/11_1/ma_11_1_pei_fokoue_final.pdfcs
dc.rights© Vysoké učení technické v Brně, Fakulta strojního inženýrství, Ústav matematikycs
dc.rights.accessopenAccessen
dc.subjectdeep neural networks
dc.subjectkernel learning machines
dc.subjectsingle hidden layer neural net- works
dc.subjectsupport vector machine
dc.subjectcross validation
dc.titleOn some similarities and differences between deep neural networks and kernel learning machinesen
dc.type.driverarticleen
dc.type.statusPeer-revieweden
dc.type.versionpublishedVersionen
eprints.affiliatedInstitution.departmentÚstav matematikycs
eprints.affiliatedInstitution.facultyFakulta strojního inženýrstvícs
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
ma_11_1_pei_fokoue_final.pdf
Size:
1.77 MB
Format:
Adobe Portable Document Format
Description:
Download
Collections
2022/1