relation: https://eprints.uet.vnu.edu.vn/eprints/id/eprint/2638/
title: On the possibility of correct concept learning in description logics
creator: Divrood, Ali Rezaei
creator: Ha, Quang Thuy
creator: Nguyen, Linh Anh
creator: Nguyen, Hung Son
subject: Information Technology (IT)
description: 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.
publisher: Springer Berlin Heidelberg
date: 2017-02-15
type: Article
type: PeerReviewed
format: application/pdf
language: en
identifier: https://eprints.uet.vnu.edu.vn/eprints/id/eprint/2638/1/%5BQG.15.22.7%5D%20Ali%20Rezaei%20Divroodi%2C%20Quang-Thuy%20Ha%2C%20Linh%20Anh%20Nguyen%2C%20Hung%20Son%20Nguyen.%20On%20the%20possibility%20of%20correct%20concept%20learning%20in%20description%20logics.%20Vietnam%20Journal%20of%20Computer%20Science%20%282017%29%201-12%2C%202017.pdf
identifier:   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     
relation: https://doi.org/10.1007/s40595-017-0094-4