Fuzzy sets complement-based gated recurrent unit

Autor:	Ferrero Jaurrieta, Mikel, Pereira Dimuro, Graçaliz, Takáč, Zdenko, Santiago, Regivan, Fernández Fernández, Francisco Javier, Bustince Sola, Humberto
Přispěvatelé:	Universidad Pública de Navarra. Departamento de Estadística, Informática y Matemáticas, Nafarroako Unibertsitate Publikoa. Estatistika, Informatika eta Matematikak Saila, Gobierno de Navarra / Nafarroako Gobernua
Jazyk:	angličtina
Rok vydání:	2021
Předmět:	Recurrent neural networks Fuzzy set complement Fuzzy negations Gated recurrent unit
Zdroj:	Academica-e. Repositorio Institucional de la Universidad Pública de Navarra instname
Popis:	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. 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.
Databáze:	OpenAIRE
Externí odkaz:	https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::60c5afc3b0e96a40af465198b47944ce https://hdl.handle.net/2454/42468 Zobrazit plný text záznamu