Fuzzy sets complement-based gated recurrent unit

Ferrero Jaurrieta, Mikel; Pereira Dimuro, Graçaliz; Takáč, Zdenko; Santiago, Regivan; Fernández Fernández, Francisco Javier; Bustince Sola, Humberto

dc.creator	Ferrero Jaurrieta, Mikel	es_ES
dc.creator	Pereira Dimuro, Graçaliz	es_ES
dc.creator	Takáč, Zdenko	es_ES
dc.creator	Santiago, Regivan	es_ES
dc.creator	Fernández Fernández, Francisco Javier	es_ES
dc.creator	Bustince Sola, Humberto	es_ES
dc.date.accessioned	2022-03-10T07:59:59Z
dc.date.available	2022-03-10T07:59:59Z
dc.date.issued	2021
dc.identifier.issn	1613-0073
dc.identifier.uri	https://hdl.handle.net/2454/42468
dc.description.abstract	Gated Recurrent Units (GRU) are neural network gated architectures that simplify other ones (suchas, LSTM) by joining gates mainly. For this, instead of using two gates, if𝑥is the first gate, standardoperation1−𝑥is used to generate the second one, optimizing the number of parameters. In this work, we interpret this information as a fuzzy set, and we generalize the standard operation using fuzzy negations, and improving the accuracy obtained with the standard one.	en
dc.description.sponsorship	Grant PID2019-108392GB-I00 funded by MCIN/AEI/10.13039/501100011033 and by Tracasa Instrumental and the Immigration Policy and Justice Department of the Government of Navarre.	en
dc.format.extent	9 p.
dc.format.mimetype	application/pdf	en
dc.language.iso	eng	en
dc.publisher	CEUR Workshop Proceedings (CEUR-WS.org)	en
dc.relation.ispartof	WILF’21: The 13th International Workshop on Fuzzy Logic and Applications, Dec. 20–22, 2021, Vietri sul Mare, Italy	en
dc.rights	© 2021 Copyright for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0).	en
dc.rights.uri	http://creativecommons.org/licenses/by/4.0/
dc.subject	Fuzzy set complement	en
dc.subject	Fuzzy negations	en
dc.subject	Recurrent neural networks	en
dc.subject	Gated recurrent unit	en
dc.title	Fuzzy sets complement-based gated recurrent unit	en
dc.type	info:eu-repo/semantics/conferenceObject	en
dc.type	Contribución a congreso / Biltzarrerako ekarpena	es
dc.contributor.department	Estadística, Informática y Matemáticas	es_ES
dc.contributor.department	Estatistika, Informatika eta Matematika	eu
dc.rights.accessRights	info:eu-repo/semantics/openAccess	en
dc.rights.accessRights	Acceso abierto / Sarbide irekia	es
dc.relation.projectID	info:eu-repo/grantAgreement/AEI/Plan Estatal de Investigación Científica y Técnica y de Innovación 2017-2020/PID2019-108392GB-I00/ES/	en
dc.type.version	info:eu-repo/semantics/publishedVersion	en
dc.type.version	Versión publicada / Argitaratu den bertsioa	es
dc.contributor.funder	Gobierno de Navarra / Nafarroako Gobernua	es

Files in this item

Name:: Ferrero_FuzzySets.pdf
Size:: 1000.Kb
Format:: PDF

View/Open

This item appears in the following Collection(s)

Comunicaciones y ponencias de congresos DEIM - EIMS Biltzarretako komunikazioak eta txostenak [75]
Comunicaciones y ponencias de congresos - Biltzarrak eta Argitalpenak [719]

Show simple item record

© 2021 Copyright for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0).

Except where otherwise noted, this item's license is described as © 2021 Copyright for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0).