Utilize este identificador para referenciar este registo: http://hdl.handle.net/10071/26524
Registo completo
Campo DCValorIdioma
dc.contributor.authorBacellar, A. T. L.-
dc.contributor.authorSusskind, Z.-
dc.contributor.authorVillon, L. A. Q.-
dc.contributor.authorMiranda, I. D. S.-
dc.contributor.authorAraújo, L. S. de.-
dc.contributor.authorDutra, D. L. C.-
dc.contributor.authorBreternitz Jr, M.-
dc.contributor.authorJohn, L. K.-
dc.contributor.authorLima, P. M. V.-
dc.contributor.authorFrança, F. M. G.-
dc.date.accessioned2022-12-05T12:46:30Z-
dc.date.available2022-12-05T12:46:30Z-
dc.date.issued2022-
dc.identifier.citationBacellar, A. T. L., Susskind, Z., Villon, L. A. Q., Miranda, I. D. S., Araújo, L. S. de., Dutra, D. L. C., Breternitz Jr., M., John, L. K., Lima, P. M. V., & França, F. M. G. (2022). Distributive thermometer: A new unary encoding for weightless neural networks. In ESANN 2022 proceedings (pp. 31-36). https://doi.org/10.14428/esann/2022.ES2022-94-
dc.identifier.isbn978287587 084-1-
dc.identifier.urihttp://hdl.handle.net/10071/26524-
dc.description.abstractThe binary encoding of real valued inputs is a crucial part of Weightless Neural Networks. The Linear Thermometer and its variations are the most prominent methods to determine binary encoding for input data but, as they make assumptions about the input distribution, the resulting encoding is sub-optimal and possibly wasteful when the assumption is incorrect. We propose a new thermometer approach that doesn’t require such assumptions. Our results show that it achieves similar or better accuracy when compared to a thermometer that correctly assumes the distribution, and accuracy gains up to 26.3% when other thermometer representations assume an unsound distribution.eng
dc.language.isoeng-
dc.publisherESANN-
dc.relationinfo:eu-repo/grantAgreement/FCT/6817 - DCRRNI ID/UIDB%2F04466%2F2020/PT-
dc.relationPOCI-01-0247-FEDER-045912-
dc.relationinfo:eu-repo/grantAgreement/FCT/6817 - DCRRNI ID/UIDP%2F04466%2F2020/PT-
dc.relation.ispartofESANN 2022 proceedings-
dc.rightsopenAccess-
dc.titleDistributive thermometer: A new unary encoding for weightless neural networkseng
dc.typeconferenceObject-
dc.event.title30th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning-
dc.event.typeConferênciapt
dc.event.locationBruges (online)eng
dc.event.date2022-
dc.pagination31 - 36-
dc.peerreviewedyes-
dc.date.updated2022-12-05T12:44:29Z-
dc.description.versioninfo:eu-repo/semantics/publishedVersion-
dc.identifier.doi10.14428/esann/2022.ES2022-94-
dc.subject.fosDomínio/Área Científica::Ciências Naturais::Ciências da Computação e da Informaçãopor
iscte.identifier.cienciahttps://ciencia.iscte-iul.pt/id/ci-pub-91314-
Aparece nas coleções:ISTAR-CRI - Comunicações a conferências internacionais

Ficheiros deste registo:
Ficheiro TamanhoFormato 
conferenceobject_91314.pdf1,54 MBAdobe PDFVer/Abrir


FacebookTwitterDeliciousLinkedInDiggGoogle BookmarksMySpaceOrkut
Formato BibTex mendeley Endnote Logotipo do DeGóis Logotipo do Orcid 

Todos os registos no repositório estão protegidos por leis de copyright, com todos os direitos reservados.