Please use this identifier to cite or link to this item: http://repositorio.unicamp.br/jspui/handle/REPOSIP/95280
Type: Artigo de evento
Title: A Recurrent Neurofuzzy Network Structure And Learning Procedure
Author: Ballini R.
Soares S.
Gomide F.
Abstract: A novel recurrent neurofuzzy network is proposed in this paper. This model is constructed from fuzzy set models of neurons. The network has a multilayer, recurrent structure whose units are modeled through triangular norms and co-norms, and weights defined within the unit interval. The learning procedure developed is based on two main paradigms: gradient search and associative reinforcement learning, respectively. That is, output layer weights are adjusted via an error gradient method whereas a reward and punishment scheme updates the hidden layer weights. The recurrent neurofuzzy network is used to develop a model of a nonlinear process. Numerical results show that the neurofuzzy network proposed here provides an accurate process model after a short period of learning time.
Editor: 
Rights: fechado
Identifier DOI: 
Address: http://www.scopus.com/inward/record.url?eid=2-s2.0-0036343216&partnerID=40&md5=6ee45d0239a6456a738f82dcfb946a3e
Date Issue: 2001
Appears in Collections:Unicamp - Artigos e Outros Documentos

Files in This Item:
File Description SizeFormat 
2-s2.0-0036343216.pdf392.87 kBAdobe PDFView/Open


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.