Classification in CPN using homogeneity based cluster re-arrangement

Author

Kovacs, Laszlo ; Terstyanszky, Gabor Z.

Author_Institution

Dept. of Inf. Technol., Univ. of Miskolc, Miskolc, Hungary

fYear

2001

fDate

4-7 Sept. 2001

Firstpage

1642

Lastpage

1646

Abstract

The classification process of the Counter Propagation neural network (CPN) is investigated. The homogeneity distribution of the codebook vectors is a key element in the accuracy of the classification process. The paper defines an appropriate homogeneity measure that is strongly correlated with the optimal misclassification error. Based on this homogeneity value, the paper proposes three modification algorithms for the original CPN classification algorithm to reduce the misclassification error in the regions of uncertain decisions. The accuracy of the proposed algorithm is tested with a case study.

Keywords

codes; neural nets; pattern classification; vectors; CPN; classification process; codebook vectors; counter propagation neural network; homogeneity based cluster rearrangement; homogeneity distribution; misclassification error reduction; optimal misclassification error; Accuracy; Classification algorithms; Clustering algorithms; Neural networks; Support vector machine classification; Training; Vectors; R-tree; classification; learning algorithms; neural networks; uncertainty;

fLanguage

English

Publisher

ieee

Conference_Titel

Control Conference (ECC), 2001 European

Conference_Location

Porto

Print_ISBN

978-3-9524173-6-2

Type

conf

Filename

7076155