Communications of the ACM
Learning regular sets from queries and counterexamples
Information and Computation
A four-valued semantics for terminological logics
Artificial Intelligence
CLASSIC: a structural data model for objects
SIGMOD '89 Proceedings of the 1989 ACM SIGMOD international conference on Management of data
COLT '88 Proceedings of the first annual workshop on Computational learning theory
LaSSIE: a knowledge-based software information system
Communications of the ACM - Special issue on software engineering
New Generation Computing - Selected papers from the international workshop on algorithmic learning theory,1990
Computational learning theory: survey and selected bibliography
STOC '92 Proceedings of the twenty-fourth annual ACM symposium on Theory of computing
On-line learning of rectangles
COLT '92 Proceedings of the fifth annual workshop on Computational learning theory
Learnability of description logics
COLT '92 Proceedings of the fifth annual workshop on Computational learning theory
PAC-learnability of determinate logic programs
COLT '92 Proceedings of the fifth annual workshop on Computational learning theory
Inference of finite automata using homing sequences
Information and Computation
Learning with malicious membership queries and exceptions (extended abstract)
COLT '94 Proceedings of the seventh annual conference on Computational learning theory
Learning from a consistently ignorant teacher
COLT '94 Proceedings of the seventh annual conference on Computational learning theory
Randomly Fallible Teachers: Learning Monotone DNF with an Incomplete Membership Oracle
Machine Learning - Special issue on computational learning theory
The Learnability of Description Logics with Equality Constraints
Machine Learning - Special issue on computational learning theory, COLT'92
Learning Conjunctive Concepts in Structural Domains
Machine Learning
Machine Learning
Machine Learning
Classification as a Query Processing Technique in the CANDIDE Semantic Data Model
Proceedings of the Fifth International Conference on Data Engineering
Learning from a consistently ignorant teacher
COLT '94 Proceedings of the seventh annual conference on Computational learning theory
Learning with unreliable boundary queries
COLT '95 Proceedings of the eighth annual conference on Computational learning theory
COLT '96 Proceedings of the ninth annual conference on Computational learning theory
Learning logic programs by using the product homomorphism method
COLT '97 Proceedings of the tenth annual conference on Computational learning theory
Corrigendum for "learnability of description logics"
COLT '95 Proceedings of the eighth annual conference on Computational learning theory
Polynomial-time learnability of logic programs with local variables from entailment
Theoretical Computer Science - Algorithmic learning theory
Learning from Entailment of Logic Programs with Local Variables
ALT '98 Proceedings of the 9th International Conference on Algorithmic Learning Theory
The description logic handbook
Partial and Informative Common Subsumers in Description Logics
Proceedings of the 2008 conference on ECAI 2008: 18th European Conference on Artificial Intelligence
A semantics and complete algorithm for subsumption in the classic description logic
Journal of Artificial Intelligence Research
Learnability of description logic programs
ILP'02 Proceedings of the 12th international conference on Inductive logic programming
Part-whole reasoning in an object-centered framework
Part-whole reasoning in an object-centered framework
Learnability of simply-moded logic programs from entailment
ASIAN'04 Proceedings of the 9th Asian Computing Science conference on Advances in Computer Science: dedicated to Jean-Louis Lassez on the Occasion of His 5th Cycle Birthday
| Hi-index | 0.00 |
Description logics, also called terminological logics, are commonly used in knowledge-based systems to describe objects and their relationships. We investigate the learnability of a typical description logic, CLASSIC, and show that CLASSIC sentences are learnable in polynomial time in the exact learning model using equivalence queries and membership queries (which are in essence, “subsumption queries”). We show that membership queries alone are insufficient for polynomial time learning of CLASSIC sentences. Combined with earlier negative results of Cohen and Hirsh showing that, given standard complexity theoretic assumptions, equivalence queries alone are insufficient (or random examples alone in the PAC setting are insufficient), this shows that both sources of information are necessary for efficient learning in that neither type alone is sufficient. In addition, we show that a modification of the algorithm deals robustly with persistent malicious two-sided classification noise in the membership queries with the probability of a misclassification bounded below 1/2.