Hyperrelations in version space

H Wang, I Düntsch, G Gediga, A Skowron

Research output: Contribution to journalArticlepeer-review

29 Citations (Scopus)
Original languageEnglish
Pages (from-to)223-241
JournalInternational Journal of Approximate Reasoning
Issue number3
Publication statusPublished (in print/issue) - 1 Jul 2004

Bibliographical note

Other Details
Version space is a machine learning paradigm developed in the 1990s, but its expressive power is limited, and thus its applicability restricted. This paper presents a version space in a much more expressive hypothesis space, where a hypothesis is a set of hypertuples that together is maximal and consistent with given data. The set of all such hypotheses is a generalised version space. Evaluations show that the generalised version space compares favourably with the state-of-the-art classifiers. The hypertuple concept has become a general knowledge representation scheme, and has been used in some later publications by the authors.

Cite this