2010 | OriginalPaper | Buchkapitel
Cluster Integration for the Cluster-Based Instance Selection
verfasst von : Ireneusz Czarnowski, Piotr Jędrzejowicz
Erschienen in: Computational Collective Intelligence. Technologies and Applications
Verlag: Springer Berlin Heidelberg
Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.
Wählen Sie Textabschnitte aus um mit Künstlicher Intelligenz passenden Patente zu finden. powered by
Markieren Sie Textabschnitte, um KI-gestützt weitere passende Inhalte zu finden. powered by
The problem addressed in this paper concerns data reduction through instance selection. The paper proposes an approach based on instance selection from clusters. The process of selection and learning is executed by a team of agents. The approach aims at obtaining a compact representation of the dataset, where the upper bound on the size of data is determined by the user. The basic assumption is that the instance selection is carried out after the training data have been grouped into clusters. The cluster initialization and integration strategies are proposed and experimentally evaluated.