Training multilayer perceptrons in the presence of measurement outliers

Author

Lo, James T. ; Bassu, Devasis

Author_Institution

Dept. of Math. & Stat., Maryland Univ., Baltimore, MD, USA

Volume

3

fYear

2001

fDate

6/23/1905 12:00:00 AM

Firstpage

2030

Abstract

Instead of the robust estimation criteria from statistics, a new training method using a continuum of modified risk-seeking criteria with a negative risk-sensitivity index is proposed for training neural networks with data containing outlying measurement noises. In contrast to the ordinary methods using a fixed training criterion or a fixed annealing schedule for the training criterion in a training session, the new method continues adjusting adaptively the risk-sensitivity index to tune to the measurement outliers for best reducing their effects on the training

Keywords

learning (artificial intelligence); multilayer perceptrons; simulated annealing; fixed annealing schedule; fixed training criterion; measurement outliers; modified risk-seeking criteria; multilayer perceptron training; negative risk-sensitivity index; neural networks; outlying measurement noises; training session; Annealing; Electronic mail; Mathematics; Multilayer perceptrons; Neural networks; Noise measurement; Noise robustness; Nonhomogeneous media; Processor scheduling; Statistics;

fLanguage

English

Publisher

ieee

Conference_Titel

Neural Networks, 2001. Proceedings. IJCNN '01. International Joint Conference on

ISSN

1098-7576

Print_ISBN

0-7803-7044-9

Type

conf

DOI

10.1109/IJCNN.2001.938478

Filename

938478