FS-EX plus: A new algorithm for the calculation of typical FS-testor set
Conference Paper
-
- Overview
-
- Research
-
- Identity
-
- Additional Document Info
-
- View All
-
Overview
abstract
-
In this paper a novel exterior escale algorithm for the calculation of FS-typical testor set of a learning matrix is proposed. This algorithm allows to use any given similarity function between objects. Besides, results of experiments done, shows the performance obtained by proposed algorithm. A comparison between proposed algorithm and an exhaustive searching algorithm, that is the only one reported on literature that can calculate the complete FS-typical testor set, is also included. © Springer-Verlag Berlin Heidelberg 2007.
publication date
published in
Research
keywords
-
Feature selection; FS-testor; Pattern recognition; Typical testor Learning algorithms; Learning systems; Matrix algebra; Object recognition; Online searching; Learning matrix; Searching algorithms; Feature extraction
Identity
Digital Object Identifier (DOI)
Additional Document Info
start page
end page
volume