Quantizing for minimum average misclassification risk

Author

Diamantini, Claudia ; Spalvieri, Arnaldo

Author_Institution

Dipt. di Elettronica, Ancona Univ., Italy

Volume

9

Issue

1

fYear

1998

fDate

1/1/1998 12:00:00 AM

Firstpage

174

Lastpage

182

Abstract

In pattern classification, a decision rule is a labeled partition of the observation space, where labels represent classes. A way to establish a decision rule is to attach a label to each code vector of a vector quantizer (VQ). When a labeled VQ is adopted as a classifier, we have to design it in such a way that high classification performance is obtained by a given number of code vectors. In this paper we propose a learning algorithm which optimizes the position of labeled code vectors in the observation space under the minimum average misclassification risk criterion

Keywords

decision theory; learning (artificial intelligence); minimisation; neural nets; nonparametric statistics; pattern classification; probability; vector quantisation; decision rule; high classification performance; labeled partition; learning algorithm; minimum average misclassification risk; observation space; pattern classification; vector quantizer; Artificial neural networks; Feature extraction; Minimization methods; Neural networks; Pattern classification; Pattern recognition; Probability; Random variables; Statistics; Vector quantization;

fLanguage

English

Journal_Title

Neural Networks, IEEE Transactions on

Publisher

ieee

ISSN

1045-9227

Type

jour

DOI

10.1109/72.655039

Filename

655039