Modeling Concept Learning Problems with Second-Order Description Logics
From International Center for Computational Logic
Modeling Concept Learning Problems with Second-Order Description Logics
Talk by Francesca Alessandra Lisi
- Location: APB 3105
- Start: 11. May 2015 at 2:50 pm
- End: 11. May 2015 at 3:50 pm
- Research group: Computational Logic
- Event series: KBS Seminar
- iCal
Among the inferences studied in Description Logics (DLs), induction has been paid increasing attention over the last decade. Indeed, useful non-standard reasoning tasks can be based on the inductive inference. Among them, Concept Learning is about the automated induction of a description for a given concept starting from classified instances of the concept. In this talk I present a formal characterization of Concept Learning in DLs which relies on recent results in Knowledge Representation and Machine Learning. Based on second-order DLs, it allows for modeling Concept Learning problems as constructive DL reasoning tasks where the construction of the solution to the problem may be subject to optimality criteria.
