Please use this identifier to cite or link to this item: http://hdl.handle.net/10397/32595
Title: Cascaded fuzzy neural network model based on syllogistic fuzzy reasoning
Authors: Duan, JC
Chung, FL 
Keywords: Cascaded fuzzy neural network
Fuzzy neural networks
Hybrid learning
Multistage fuzzy neural networks
Syllogistic fuzzy reasoning
Issue Date: 2001
Publisher: Institute of Electrical and Electronics Engineers
Source: IEEE transactions on fuzzy systems, 2001, v. 9, no. 2, p. 293-306 How to cite?
Journal: IEEE transactions on fuzzy systems 
Abstract: In recent years, there has been an increasing interest in the fusion of neural networks and fuzzy logic. Most of the existing fuzzy neural network (FNN) models have been proposed to implement different types of single-stage fuzzy reasoning mechanisms. Single-stage fuzzy reasoning, however, is only the most basic among a human being's various types of reasoning mechanisms. Syllogistic fuzzy reasoning, where the consequence of a rule in one reasoning stage is passed to the next stage as a fact, is essential to effectively build up a large scale system with high level intelligence. In view of the fact that the fusion of syllogistic fuzzy logic and neural networks has not been sufficiently studied, a new FNN model based on syllogistic fuzzy reasoning, termed cascaded FNN (CFNN), is proposed in this paper. From the stipulated input-output data pairs, the model can generate an appropriate syllogistic fuzzy rule set through structure (genetic) learning and parameter (back-propagation) learning procedures proposed in this paper. In addition, we particularly discuss and analyze the performance of the proposed model in terms of approximation ability and robustness as compared with single-stage FNN models. The effectiveness of the proposed CFNN model is demonstrated through simulating two benchmark problems in fuzzy control and nonlinear function approximation domain.
URI: http://hdl.handle.net/10397/32595
ISSN: 1063-6706
EISSN: 1941-0034
DOI: 10.1109/91.919250
Appears in Collections:Journal/Magazine Article

Access
View full-text via PolyU eLinks SFX Query
Show full item record

SCOPUSTM   
Citations

39
Last Week
0
Last month
1
Citations as of Aug 14, 2017

WEB OF SCIENCETM
Citations

30
Last Week
0
Last month
0
Citations as of Aug 21, 2017

Page view(s)

34
Last Week
2
Last month
Checked on Aug 20, 2017

Google ScholarTM

Check

Altmetric



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