Title :
Dynamic multilayer neural network for nonlinear system identification
Author :
Sanchez, Edgar N. ; Poznyak, Alexander S. ; Yu, Wen
Author_Institution :
CINVESTAV, Gaudalajara, Mexico
Abstract :
To identify online a quite general class of nonlinear systems, this paper proposes a new stable learning law for dynamic multilayer neural networks. A Lyapunov-like analysis is used to derive this stable learning procedure for the hidden layer as well as for the output layer
Keywords :
Lyapunov methods; feedforward neural nets; identification; learning (artificial intelligence); nonlinear systems; Lyapunov-like analysis; dynamic multilayer neural network; hidden layer; identification; learning law; nonlinear system; output layer; Control systems; Differential equations; Linear systems; Lyapunov method; Multi-layer neural network; Neural networks; Nonlinear control systems; Nonlinear dynamical systems; Nonlinear systems; Riccati equations;
Conference_Titel :
Neural Networks, 1999. IJCNN '99. International Joint Conference on
Conference_Location :
Washington, DC
Print_ISBN :
0-7803-5529-6
DOI :
10.1109/IJCNN.1999.832712