Using the Geometrical Distribution of Prototypes for Training Set Condensing

Lozano, M. ; Sánchez, JS. ; Pla, F.

Resumen: In this paper, some new approaches to training set size reduction are presented. These schemes basically consist of defining a small number of prototypes that represent all the original instances. Although the ultimate aim of the algorithms proposed here is to obtain a strongly reduced training set, the performance is empirically evaluated over nine real datasets by comparing the reduction rate and the classification accuracy with those of other condensing techniques.

Idioma: Inglés

Año: 2004

Publicado en: Lecture Notes in Computer Science 3040 (2004), 618-627
ISSN: 0302-9743

Factor impacto JCR: 0.513 (2004)

Categ. JCR: COMPUTER SCIENCE, THEORY & METHODS rank: 53 / 70 = 0.757 (2004) - Q4 - T3
Categ. JCR: COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE rank: 58 / 77 = 0.753 (2004) - Q4 - T3

Tipo y forma: Artículo (PostPrint)