Title :
Learning convergence analysis for Takagi-Sugeno Fuzzy Neural Networks
Author :
Chiang, Tung-sheng ; Liu, Peter ; Yang, Chang-En
Author_Institution :
Dept. of Electr. Eng., Ching-Yun Univ., Jungli, Taiwan
Abstract :
In this paper, we provide a mathematical formulation of the Takagi-Sugeno Fuzzy Neural Network (TS-FNN) to study convergence properties. Note that we describe both information retrieval and learning rules by algebraic equations in matrix form. We then investigate the convergence characteristics and learning behaviors for the TS-FNN by use of these algebraic equations and the eigenvalues of derived matrices. Numerical examples are carried out to further verify the analysis.
Keywords :
convergence of numerical methods; eigenvalues and eigenfunctions; fuzzy control; learning systems; matrix algebra; neurocontrollers; TS-FNN; Takagi-Sugeno fuzzy neural networks; algebraic equations; convergence characteristics; convergence properties; information retrieval; learning behaviors; learning convergence analysis; learning rules; matrices eigenvalues; matrix form; Convergence; Eigenvalues and eigenfunctions; Equations; Fuzzy control; Fuzzy neural networks; Mathematical model; Vectors;
Conference_Titel :
Fuzzy Systems (FUZZ-IEEE), 2012 IEEE International Conference on
Conference_Location :
Brisbane, QLD
Print_ISBN :
978-1-4673-1507-4
Electronic_ISBN :
1098-7584
DOI :
10.1109/FUZZ-IEEE.2012.6251318
