2012 | OriginalPaper | Buchkapitel
Artificial Negative Selection: Searching for an Appropriate Application Scenario
verfasst von : Yevgen Nebesov
Erschienen in: Bio-Inspired Models of Networks, Information, and Computing Systems
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
Despite numerous theoretical investigations on Artificial negative selection (ANS), there are still no useful scenarios in which this paradigm would outperform mainstream machine learning, statistical classification methods or other bio-inspired classification approaches. The aim of this paper is to identify main characteristics and requirements of a useful ANS scenario. Our investigations on this question led us to the need to extend the original ANS model proposed by Forrest et al. in [4]. The motivation of our work relies on the observation that biological mechanisms are not isolated mechanisms with a broad application range. They are only suitable for highly specific tasks and they might only be efficient in interaction with the rest of the biological environment.