Optimal, matching-score network for pattern classification

Author

Luk, Andrew ; Leung, Wai-Fung

Author_Institution

Dept. of Electron. Eng., City Polytech. of Hong Kong, Kowloon, Hong Kong

Volume

ii

fYear

1994

fDate

19-22 Apr 1994

Abstract

This paper presents a design method for an optimal matching-score (MS) network with exponential and sigmoid activation functions. By using a new orthogonal learning process, the proposed net is capable of learning new patterns by growing its hidden layer and without recomputing the entire interconnection weight matrices. Simulation results on signal classification and character recognition show that the MS net is highly robust to noise. Besides, the generalization capability of the net is shown superior than that of the backpropagation net

Keywords

feedforward neural nets; learning (artificial intelligence); matrix inversion; multilayer perceptrons; pattern classification; transfer functions; character recognition; exponential activation functions; hidden layer; matrix inversion method; noise robustness; optimal matching-score network; orthogonal learning process; pattern classification; sigmoid activation functions; signal classification; simulation results; two-layer feedforward matching-score net; Backpropagation algorithms; Cities and towns; Design engineering; Design methodology; Multi-layer neural network; Neurons; Optimal matching; Pattern classification; Pattern matching; Symmetric matrices;

fLanguage

English

Publisher

ieee

Conference_Titel

Acoustics, Speech, and Signal Processing, 1994. ICASSP-94., 1994 IEEE International Conference on

Conference_Location

Adelaide, SA

ISSN

1520-6149

Print_ISBN

0-7803-1775-0

Type

conf

DOI

10.1109/ICASSP.1994.389585

Filename

389585