Comments on "Dynamical Optimal Training for Interval Type-2 Fuzzy Neural Network (T2FNN)

Author

Hagras, Hani

Author_Institution

Dept. of Comput. Sci., Essex Univ., Colchester

Volume

36

Issue

5

fYear

2006

Firstpage

1206

Lastpage

1209

Abstract

In this comment, it will be shown that the backpropagation (BP) equations by Wang are not correct. These BP equations were used to tune the parameters of the antecedent type-2 membership functions as well as the consequent part of the interval type-2 fuzzy neural networks (T2FNNs). These incorrect equations would have led to erroneous results, and hence this might affect the comparisons and findings presented by Wang This comment will highlight the correct BP tuning equations for the T2FNN

Keywords

backpropagation; fuzzy logic; fuzzy neural nets; fuzzy systems; BP tuning equation; backpropagation; dynamical optimal training; interval type-2 fuzzy neural network; type-2 fuzzy logic system; type-2 membership function; Backpropagation algorithms; Computer science; Equations; Fuzzy logic; Fuzzy neural networks; Fuzzy sets; Fuzzy systems; Genetic algorithms; Heuristic algorithms; Uncertainty; Interval type-2 fuzzy neural network (T2FNN); type-2 fuzzy logic systems; Algorithms; Artificial Intelligence; Feedback; Fuzzy Logic; Neural Networks (Computer); Pattern Recognition, Automated;

fLanguage

English

Journal_Title

Systems, Man, and Cybernetics, Part B: Cybernetics, IEEE Transactions on

Publisher

ieee

ISSN

1083-4419

Type

jour

DOI

10.1109/TCSI.2006.873184

Filename

1703662