Title :
Reproducing chaos by variable structure recurrent neural networks
Author :
Felix, Ramon A. ; Sanchez, Edgar N. ; Chen, Guanrong
Author_Institution :
CINVESTAV, Guadalajara, Spain
Abstract :
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.
Keywords :
chaos; computational complexity; identification; neurocontrollers; nonlinear control systems; recurrent neural nets; variable structure systems; chaos reproduction; chaotic system; computational complexity; identification error; neural network identifier; variable structure recurrent neural network; Chaos; Computational complexity; Control system synthesis; Control systems; Neural networks; Nonlinear control systems; Nonlinear systems; Orbits; Recurrent neural networks; Switched systems; Chaos generation; identification; recurrent neural networks; variable structure system; Algorithms; Artificial Intelligence; Computer Simulation; Decision Support Techniques; Feedback; Logistic Models; Neural Networks (Computer); Nonlinear Dynamics; Pattern Recognition, Automated;
Journal_Title :
Neural Networks, IEEE Transactions on
DOI :
10.1109/TNN.2004.836236
