Fuzzy sets complement-based gated recurrent unit

View/ Open
Date
2021Author
Version
Acceso abierto / Sarbide irekia
Type
Contribución a congreso / Biltzarrerako ekarpena
Version
Versión publicada / Argitaratu den bertsioa
Project Identifier
Impact
|
nodoi-noplumx
|
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 ...
[++]
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. [--]
Subject
Fuzzy set complement,
Fuzzy negations,
Recurrent neural networks,
Gated recurrent unit
Publisher
CEUR Workshop Proceedings (CEUR-WS.org)
Published in
WILF’21: The 13th International Workshop on Fuzzy Logic and Applications, Dec. 20–22, 2021, Vietri sul Mare, Italy
Departament
Universidad Pública de Navarra. Departamento de Estadística, Informática y Matemáticas /
Nafarroako Unibertsitate Publikoa. Estatistika, Informatika eta Matematika Saila
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.