2013 | OriginalPaper | Buchkapitel
Markov Network Revision: On the Handling of Inconsistencies
verfasst von : Jörg Gebhardt, Aljoscha Klose, Jan Wendler
Erschienen in: Computational Intelligence in Intelligent Data Analysis
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
Graphical models are of high relevance for complex industrial applications. The Markov network approach is one of their most prominent representatives and an important tool to structure uncertain knowledge about high-dimensional domains in order to make reasoning in such domains feasible. Compared to
conditioning
the represented probability distribution on given evidence, the important belief change operation called
revision
has been almost entirely disregarded in the past, although it is of utmost relevance for real world applications. In this paper we focus on the problem of
inconsistencies
during revision in Markov networks. We formally introduce the revision operation and propose methods to specify, identify, and resolve inconsistencies. The revision and its inconsistency management has proven to be successful in a complex application for item planning and capacity management in the automotive industry at Volkswagen Group.