Title :
Dynamic neural networks for nonlinear systems identification
Author :
Sanchez, Edgar N.
Author_Institution :
FIME, Univ. Autonoma de Nuevo Leon, San Nicolas de los Garza, Mexico
Abstract :
This paper approaches nonlinear system identification as operator approximation. A neural network, which can identify nonlinear systems, is presented. The identification is performed by the arbitrarily well approximation of time-invariant causal and continuous operators, which have fading memory. A theorem about this property is stated and proved
Keywords :
approximation theory; identification; neural nets; nonlinear systems; continuous operator; dynamic neural networks; fading memory; identification; nonlinear systems; operator approximation; time-invariant causal operator; Biological system modeling; Fading; Hopfield neural networks; Neural networks; Neurons; Nonlinear control systems; Nonlinear dynamical systems; Nonlinear systems; System identification; Vectors;
Conference_Titel :
Decision and Control, 1994., Proceedings of the 33rd IEEE Conference on
Conference_Location :
Lake Buena Vista, FL
Print_ISBN :
0-7803-1968-0
DOI :
10.1109/CDC.1994.411513
