Utilize este identificador para referenciar este registo:
http://hdl.handle.net/10071/26522
Registo completo
Campo DC | Valor | Idioma |
---|---|---|
dc.contributor.author | Susskind, Z. | - |
dc.contributor.author | Bacellar, A. T. L. | - |
dc.contributor.author | Arora, A. | - |
dc.contributor.author | Villon, L. A. Q. | - |
dc.contributor.author | Mendanha, R. | - |
dc.contributor.author | Araújo, L. S. de. | - |
dc.contributor.author | Dutra, D. L. C. | - |
dc.contributor.author | Lima, P. M. V. | - |
dc.contributor.author | França, F. M. G. | - |
dc.contributor.author | Miranda, I. D. S. | - |
dc.contributor.author | Breternitz Jr., M. | - |
dc.contributor.author | John, L. K. | - |
dc.date.accessioned | 2022-12-05T12:31:40Z | - |
dc.date.available | 2022-12-05T12:31:40Z | - |
dc.date.issued | 2022 | - |
dc.identifier.citation | Susskind, Z., Bacellar, A. T. L., Arora, A., Villon, L. A. Q., Mendanha, R., Araújo, L. S. de., Dutra, D. L. C., Lima, P. M. V., França, F. M. G., Miranda, I. D. S., Breternitz Jr., M., & John, L. K. (2022). Pruning weightless neural networks. In ESANN 2022 proceedings (pp. 37-42). https://doi.org/10.14428/esann/2022.ES2022-55 | - |
dc.identifier.isbn | 978287587084-1 | - |
dc.identifier.uri | http://hdl.handle.net/10071/26522 | - |
dc.description.abstract | Weightless neural networks (WNNs) are a type of machine learning model which perform prediction using lookup tables (LUTs) instead of arithmetic operations. Recent advancements in WNNs have reduced model sizes and improved accuracies, reducing the gap in accuracy with deep neural networks (DNNs). Modern DNNs leverage “pruning” techniques to reduce model size, but this has not previously been explored for WNNs. We propose a WNN pruning strategy based on identifying and culling the LUTs which contribute least to overall model accuracy. We demonstrate an average 40% reduction in model size with at most 1% reduction in accuracy. | eng |
dc.language.iso | eng | - |
dc.publisher | ESANN | - |
dc.relation | 3015.001/3016.00 | - |
dc.relation | POCI-01-0247-FEDER-045912 | - |
dc.relation | info:eu-repo/grantAgreement/FCT/6817 - DCRRNI ID/UIDP%2F04466%2F2020/PT | - |
dc.relation | info:eu-repo/grantAgreement/FCT/6817 - DCRRNI ID/UIDB%2F04466%2F2020/PT | - |
dc.relation.ispartof | ESANN 2022 proceedings | - |
dc.rights | openAccess | - |
dc.title | Pruning weightless neural networks | eng |
dc.type | conferenceObject | - |
dc.event.title | 30th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning | - |
dc.event.type | Conferência | pt |
dc.event.location | Bruges (online) | eng |
dc.event.date | 2022 | - |
dc.pagination | 37 - 42 | - |
dc.peerreviewed | yes | - |
dc.date.updated | 2022-12-05T12:27:28Z | - |
dc.description.version | info:eu-repo/semantics/publishedVersion | - |
dc.identifier.doi | 10.14428/esann/2022.ES2022-55 | - |
dc.subject.fos | Domínio/Área Científica::Ciências Naturais::Ciências da Computação e da Informação | por |
iscte.identifier.ciencia | https://ciencia.iscte-iul.pt/id/ci-pub-91315 | - |
Aparece nas coleções: | ISTAR-CRI - Comunicações a conferências internacionais |
Ficheiros deste registo:
Ficheiro | Tamanho | Formato | |
---|---|---|---|
conferenceobject_91315.pdf | 1,44 MB | Adobe PDF | Ver/Abrir |
Todos os registos no repositório estão protegidos por leis de copyright, com todos os direitos reservados.