Using multiple statistical prototypes to classify continuously valued data

Author

Ventura, Dan ; Martinez, Tony R.

Author_Institution

Dept. of Comput. Sci., Brigham Young Univ., Provo, UT, USA

fYear

1995

fDate

20-23 Sep 1995

Firstpage

238

Lastpage

245

Abstract

Multiple statistical prototypes (MSP) is a modification of a standard minimum distance classification scheme that generates multiple prototypes per class using a modified greedy heuristic. Empirical comparison of MSP with other well-known learning algorithms shows MSP to be a robust algorithm that uses a very simple premise to produce good generalization and achieve parsimonious hypothesis representation

Keywords

generalisation (artificial intelligence); learning (artificial intelligence); parallel processing; pattern classification; statistical analysis; data classification; generalization; greedy heuristic; learning algorithms; minimum distance classification; multiple statistical prototypes; Computer science; Electronic mail; Input variables; Prototypes; Radial basis function networks; Robustness;

fLanguage

English

Publisher

ieee

Conference_Titel

Neuroinformatics and Neurocomputers, 1995., Second International Symposium on

Conference_Location

Rostov on Don

Print_ISBN

0-7803-2512-5

Type

conf

DOI

10.1109/ISNINC.1995.480863

Filename

480863

Link To Document

https://search.isc.ac/dl/search/defaultta.aspx?DTC=49&DC=3069597