Identification Using Feedforward Networks

1 March 1995

journal article
Published by MIT Press in Neural Computation

Vol. 7 (2) , 349-369
https://doi.org/10.1162/neco.1995.7.2.349

Abstract

This paper is concerned with the identification of an unknown nonlinear dynamic system when only the inputs and outputs are accessible for measurement. Specifically we investigate the use of feedforward neural networks as models for the input-output behavior of such systems. Relying on the approximation capabilities of feedforward neural networks and under mild assumptions regarding the properties of the underlying nonlinear system, it is shown that there exists a feedforward network that for almost all inputs (an open and dense set) will display the input-output behavior of the system.

Keywords

This publication has 2 references indexed in Scilit:

Multilayer feedforward networks are universal approximators
Neural Networks, 1989
Input-output parametric models for non-linear systems Part I: deterministic non-linear systems
International Journal of Control, 1985