Learning Composite Concepts
1998 (English)In: Proceedings of the International Workshop on Description Logics, 1998, 147-152 p.Conference paper (Refereed)
This paper proposes a framework to learn concepts from different kinds of observations. We define a language to describe meta-concepts, that represent the sets of possible concepts that can be the result of learning given a set of observations. The kinds of observations that we have studied are subsumption, membership and part-of. We exemplify the framework by showing how composite concepts can be learned in a specific description logic and we show that previous machine learning approaches in description logics can be reformulated in our framework. 1 Introduction In [LM96] the problem of learning composite concepts was formulated in the framework of description logics. Description logics are restricted variants of firstorder logic providing a form of logical bias that dates back to semantic networks. Some recent work investigates concept learning in the context of description logics
Learning Composite Concepts.. Available from: http://www.researchgate.net/publication/220956947_Learning_Composite_Concepts [accessed Jul 1, 2015].
Place, publisher, year, edition, pages
1998. 147-152 p.
IdentifiersURN: urn:nbn:se:liu:diva-119302OAI: oai:DiVA.org:liu-119302DiVA: diva2:820754
International Workshop on Description Logics