Nonlinear model structure detection using optimum experimental design and orthogonal least squares

Author

Hong, X. ; Harris, C.J.

Author_Institution

Dept. of Electron. & Comput. Sci., Southampton Univ., UK

Volume

12

Issue

2

fYear

2001

fDate

3/1/2001 12:00:00 AM

Firstpage

435

Lastpage

439

Abstract

A very efficient learning algorithm for model subset selection is introduced based on a new composite cost function that simultaneously optimizes the model approximation ability and model adequacy. The derived model parameters are estimated via forward orthogonal least squares, but the subset selection cost function includes an A-optimality design criterion to minimize the variance of the parameter estimates that ensures the adequacy and parsimony of the final model. An illustrative example is included to demonstrate the effectiveness of the new approach

Keywords

computational complexity; design of experiments; learning (artificial intelligence); least squares approximations; minimisation; neural nets; nonlinear systems; parameter estimation; A-optimality design criterion; composite cost function; efficient learning algorithm; forward orthogonal least squares; model adequacy; model approximation ability; model subset selection; nonlinear model structure detection; optimum experimental design; parameter estimation; subset selection cost function; variance minimization; Approximation algorithms; Cost function; Design for experiments; Design optimization; Least squares approximation; Least squares methods; Linear regression; Neural networks; Parameter estimation; Predictive models;

fLanguage

English

Journal_Title

Neural Networks, IEEE Transactions on

Publisher

ieee

ISSN

1045-9227

Type

jour

DOI

10.1109/72.914539

Filename

914539