Bounding the performance of neural network estimators, given only a set of training data

Author

Liang, Weibo ; Manry, Michael T. ; Yu, Qiang ; Apollo, Steven J. ; Dawson, Michael S. ; Fung, Adrian K.

Author_Institution

Dept. of Electr. Eng., Texas Univ., Arlington, TX, USA

Volume

2

fYear

1994

fDate

31 Oct-2 Nov 1994

Firstpage

912

Abstract

Uses a neural network method for obtaining a stochastic Cramer-Rao bound on estimates, given only the training data. The Cramer-Rao bounds can be used (1) to help determine when neural net training should be stopped, (2) to re-order the network inputs according to their contributions to the bounds, and (3) to eliminate less useful inputs. The convergence of the modelling procedure is shown. Examples are provided to illustrate the method

Keywords

convergence; estimation theory; learning (artificial intelligence); multilayer perceptrons; signal detection; stochastic processes; convergence; modelling procedure; network inputs; neural network estimators; performance; stochastic Cramer-Rao bound; training data; Convergence; Equations; Estimation theory; Maximum likelihood estimation; Multilayer perceptrons; Neural networks; Parameter estimation; Postal services; Stochastic processes; Training data;

fLanguage

English

Publisher

ieee

Conference_Titel

Signals, Systems and Computers, 1994. 1994 Conference Record of the Twenty-Eighth Asilomar Conference on

Conference_Location

Pacific Grove, CA

ISSN

1058-6393

Print_ISBN

0-8186-6405-3

Type

conf

DOI

10.1109/ACSSC.1994.471593

Filename

471593