A Research on Chaotic Recurrent Fuzzy Neural Network and Its Convergence

Author

Tang, Mo ; Wang, Ke Jun ; Zhang, Yan

Author_Institution

Univ. of Harbin Eng., Harbin

fYear

2007

fDate

5-8 Aug. 2007

Firstpage

682

Lastpage

687

Abstract

In this paper, a type of chaotic recurrent fuzzy neural network (CRFNN) model is proposed. The CRFNN model add chaotic map in the membership function layer of a RFNN. A generalized dynamic back propagation algorithm (DBP) is developed to automatically construct the CRFNN. To guarantee the convergence by Lyapunov function, the online learning rate adjusting range is given. Simulation results of identifying chaotic system show that, CRFNN has better performance than normal method and the adaptive learning rate could improve efficiency and decrease approximation errors.

Keywords

Lyapunov methods; backpropagation; chaos; convergence; fuzzy control; fuzzy neural nets; neurocontrollers; nonlinear control systems; recurrent neural nets; Lyapunov function; chaotic recurrent fuzzy neural network; convergence; generalized dynamic back propagation algorithm; membership function layer; online adaptive learning rate; Automation; Chaos; Convergence; Fuzzy control; Fuzzy neural networks; Heuristic algorithms; Lyapunov method; Neurons; Nonlinear dynamical systems; Nonlinear systems; Chaos; Convergence; Dynamic back propagation algorithm; Recurrent fuzzy neural network;

fLanguage

English

Publisher

ieee

Conference_Titel

Mechatronics and Automation, 2007. ICMA 2007. International Conference on

Conference_Location

Harbin

Print_ISBN

978-1-4244-0828-3

Electronic_ISBN

978-1-4244-0828-3

Type

conf

DOI

10.1109/ICMA.2007.4303626

Filename

4303626