A neural network training algorithm utilizing multiple sets of linear equations

Author

Chen, Hung-Han ; Manry, Michael T.

Author_Institution

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

fYear

1996

fDate

3-6 Nov. 1996

Firstpage

1166

Abstract

A fast algorithm is presented for the training of multilayer perceptron neural networks. In each iteration, there are two passes through the training data. In the first pass, linear equations are solved for the output weights. In the second data pass, linear equations are solved for hidden unit weight changes. Full batching is used in both data passes. An algorithm is described for calculating the learning factor for use with the hidden weights. It is shown that the technique is significantly faster than standard output weight optimization-backpropagation.

Keywords

learning (artificial intelligence); multilayer perceptrons; batching; data passes; fast algorithm; hidden unit weight; learning factor; linear equations; multilayer perceptron neural networks; neural network training algorithm; output weight optimization-backpropagation; output weights; surface scattering parameters; training data; Additives; Backpropagation algorithms; Equations; Feeds; Joining processes; Mean square error methods; Multi-layer neural network; Multilayer perceptrons; Neural networks; Training data;

fLanguage

English

Publisher

ieee

Conference_Titel

Signals, Systems and Computers, 1996. Conference Record of the Thirtieth Asilomar Conference on

Conference_Location

Pacific Grove, CA, USA

ISSN

1058-6393

Print_ISBN

0-8186-7646-9

Type

conf

DOI

10.1109/ACSSC.1996.599128

Filename

599128