On the possibility of correct concept learning in description logics

Divrood, Ali Rezaei and Ha, Quang Thuy and Nguyen, Linh Anh and Nguyen, Hung Son (2017) On the possibility of correct concept learning in description logics. Vietnam Journal of Computer Science, 2017 . pp. 1-12. ISSN 2196-8888; Online 2196-8896

PDF Download (772kB)

Abstract

It is well known that any Boolean function in classical propositional calculus can be learned correctly if the training information system is good enough. In this paper, we extend that result for description logics. We prove that any concept in any description logic that extends ALCALC with some features amongst I (inverse roles), QkQk (qualified number restrictions with numbers bounded by a constant k), and SelfSelf (local reflexivity of a role) can be learned correctly if the training information system (specified as a finite interpretation) is good enough. That is, there exists a learning algorithm such that, for every concept C of those logics, there exists a training information system such that applying the learning algorithm to it results in a concept equivalent to C. For this result, we introduce universal interpretations and bounded bisimulation in description logics and develop an appropriate learning algorithm. We also generalize common types of queries for description logics, introduce interpretation queries, and present some consequences.

Item Type:	Article
Subjects:	Information Technology (IT)
Divisions:	Faculty of Information Technology (FIT)
Depositing User:	Hà Quang Thụy
Date Deposited:	16 Nov 2017 04:29
Last Modified:	16 Nov 2017 04:29
URI:	http://eprints.uet.vnu.edu.vn/eprints/id/eprint/2638

Actions (login required)

View Item