Optimized Nearest-Neighbor Classifiers Using Generated Instances
- We present a novel approach to classification, based on a tight coupling of instancebased learning and a genetic algorithm. In contrast to the usual instance-based learning setting, we do not rely on (parts of) the given training set as the basis of a nearestneighbor classifier, but we try to employ artificially generated instances as concept prototypes. The extremely hard problem of finding an appropriate set of concept prototypes is tackled by a genetic search procedure with the classification accuracy on the given training set as evaluation criterion for the genetic fitness measure. Experiments with artificial datasets show that - due to the ability to find concise and accurate concept descriptions that contain few, but typical instances - this classification approach is considerably robust against noise, untypical training instances and irrelevant attributes. These favorable (theoretical) properties are corroborated using a number of hard real-world classification problems.
Verfasser*innenangaben: | Matthias Fuchs, Andreas Abecker |
---|---|
URN: | urn:nbn:de:hbz:386-kluedo-625 |
Schriftenreihe (Bandnummer): | LSA Report (96,2E) |
Dokumentart: | Preprint |
Sprache der Veröffentlichung: | Englisch |
Jahr der Fertigstellung: | 1996 |
Jahr der Erstveröffentlichung: | 1996 |
Veröffentlichende Institution: | Technische Universität Kaiserslautern |
Datum der Publikation (Server): | 03.04.2000 |
Freies Schlagwort / Tag: | Genetic Algorithm; Instance-based Learning; Nearest-Neighbor Classification |
Fachbereiche / Organisatorische Einheiten: | Kaiserslautern - Fachbereich Informatik |
DDC-Sachgruppen: | 0 Allgemeines, Informatik, Informationswissenschaft / 004 Informatik |
Lizenz (Deutsch): | Standard gemäß KLUEDO-Leitlinien vor dem 27.05.2011 |