Reproducing chaos by variable structure recurrent neural networks

被引：7
作者：
Felix, RA [1 ]
Sanchez, EN
Chen, GR
机构：
[1] CINVESTAV, Unidad Guadalajara, Guadalajara, Jalisco, Mexico
[2] City Univ Hong Kong, Dept Elect Engn, Hong Kong, Hong Kong, Peoples R China
来源：
IEEE TRANSACTIONS ON NEURAL NETWORKS | 2004年 / 15卷 / 06期
关键词：
chaos generation; identification; recurrent neural networks; variable structure system;
D O I：
10.1109/TNN.2004.836236
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
In this paper, we present a new approach for chaos reproduction using variable structure recurrent neural networks (VSRNN). A neural network identifier is designed, with a variable structure that will change according to its output performance as compared to the given orbits of an unknown chaotic systems. A tradeoff between identification errors and computational complexity is discussed.
引用
收藏
页码：1450 / 1457
页数：8
相关论文
共 13 条
[1]  
[Anonymous], 1996, NONLINEAR SYSTEM
[2]   Multiple Lyapunov functions and other analysis tools for switched and hybrid systems [J].
Branicky, MS .
IEEE TRANSACTIONS ON AUTOMATIC CONTROL, 1998, 43 (04) :475-482
[3]  
Chen G., 1998, CHAOS ORDER METHODOL
[4]  
Cotter N E, 1990, IEEE Trans Neural Netw, V1, P290, DOI 10.1109/72.80265
[5]  
HUNT KJ, 1995, NEURAL NETWORKS ENG
[6]  
Ioannou PA., 1996, ROBUST ADAPTIVE CONT, V1
[7]   Dynamical neural networks that ensure exponential identification error convergence [J].
Kosmatopoulos, EB ;
Christodoulou, MA ;
Ioannou, PA .
NEURAL NETWORKS, 1997, 10 (02) :299-314
[8]  
MANCILLA JL, 2000, P IEEE CDC 2000 SYDN
[9]   ADAPTIVE-CONTROL OF UNKNOWN PLANTS USING DYNAMICAL NEURAL NETWORKS [J].
ROVITHAKIS, GA ;
CHRISTODOULOU, MA .
IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS, 1994, 24 (03) :400-412
[10]   Using dynamic neural networks to generate chaos: An inverse optimal control approach [J].
Sanchez, EN ;
Perez, JP ;
Chen, GR .
INTERNATIONAL JOURNAL OF BIFURCATION AND CHAOS, 2001, 11 (03) :857-863
12