2003 | OriginalPaper | Buchkapitel
Genetic Programming with Boosting for Ambiguities in Regression Problems
verfasst von : Grégory Paris, Denis Robilliard, Cyril Fonlupt
Erschienen in: Genetic Programming
Verlag: Springer Berlin Heidelberg
Enthalten in: Professional Book Archive
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
Facing ambiguities in regression problems is a challenge. There exists many powerful evolutionary schemes to deal with regression, however, these techniques do not usually take into account ambiguities (i.e. the existence of 2 or more solutions for some or all points in the domain). Nonetheless ambiguities are present in some real world inverse problems, and it is interesting in such cases to provide the user with a choice of possible solutions. We propose in this article an approach based on boosted genetic programming in order to propose several solutions when ambiguities are detected.