Filters








9,125 Hits in 2.9 sec

Learnability of Description Logic Programs [chapter]

Kietz Jörg-Uwe
2003 Lecture Notes in Computer Science  
By allowing description logic terms as predicates of literals in datalog rules, it extends the normal bias used in ILP as it allows the use of all quantified variables in the body of a clause.  ...  On the theoretical side, this allows us to transfer the learnability results known for ILP to Carin-ALN rules.  ...  The presentation of the paper was founded by the European commission NoE-project ILPNet2 (INCO 977102).  ... 
doi:10.1007/3-540-36468-4_8 fatcat:v27e4aywhrgqrbyidrgmeeeusu

The learnability of description logics with equality constraints

William W. Cohen, Haym Hirsh
1994 Machine Learning  
In this paper, we will study instead the learnability of the restricted first-order logics known as "description logics", also sometimes called "terminological logics" or "KL-ONE-type languages".  ...  Description logics are also subsets of predicate calculus, but are expressed using a different syntax, allowing a different set of syntactic restrictions to be explored.  ...  The authors would like to thank Rob Schapire and Mike Kearns for comments on a draft of the paper, and Alex Borgida for comments on early version of some of the proofs.  ... 
doi:10.1007/bf00993470 fatcat:cz3o3setafh65iu27urlf7zdtm

Ontology Learning from Interpretations in Lightweight Description Logics [chapter]

Szymon Klarman, Katarina Britz
2016 Lecture Notes in Computer Science  
We characterize the key constraints on the models that warrant finite learnability of TBoxes expressed in selected fragments of the Description Logic EL and define corresponding learning algorithms.  ...  In this paper, we study the problem of learning Description Logic TBoxes from interpretations, which naturally translates to the task of ontology learning from data.  ...  We characterize the key constraints on the models that warrant finite learnability of TBoxes expressed in selected fragments of the Description Logic EL and define corresponding learning algorithms.  ... 
doi:10.1007/978-3-319-40566-7_6 fatcat:2yq73py6wrckfbhr3g2eb2sxia

Characterising Modal Formulas with Examples [article]

Balder ten Cate, Raoul Koudijs
2022 arXiv   pre-print
We initiate the study of finite characterizations and exact learnability of modal languages.  ...  This definition can be applied not only to the basic modal logic K, but to arbitrary normal modal logics.  ...  Our interest in exact learnability is itself motivated by applications in description logic.  ... 
arXiv:2206.06049v1 fatcat:qlcnb2jj4vcypocq3xseoaiyqu

Learning Query Inseparable ELH Ontologies (Extended Abstract)

Ana Ozaki, Cosimo Persia, Andrea Mazzullo
2020 International Workshop on Description Logics  
As illustrated in Example 2, query inseparability is a less strict notion than logical equivalence, investigated by Konev et al. [4, 5, 3] . We assume that the  ...  In this extended abstract we give an overview of our work [6] , published at AAAI 2020, on learning description logic (DL) ontologies.  ...  Table 1 summarises, in the first two columns, polynomial query learnability results for finding a logically equivalent hypothesis, and our query inseparability results.  ... 
dblp:conf/dlog/OzakiPM20 fatcat:mq7iyiekyve2fcbtqttxlsig54

Learning Ontologies with Epistemic Reasoning: The EL Case (Extended Abstract)

Ana Ozaki, Nicolas Troquard
2019 International Workshop on Description Logics  
Polynomial learnability. Each class denotes the set of frameworks that are polynomial query learnable in the corresponding learning model.  ...  An analogous notion depending on the size and number of queries is used for polynomial query learnability [8] .  ... 
dblp:conf/dlog/OzakiT19 fatcat:yzr5n2ujmzhbbcjtulj6h2xrnm

Bayesian Inductive Logic Programming [chapter]

Stephen Muggleton
1994 Machine Learning Proceedings 1994  
Time-bounded logic programs have been shown to be polynomially U-learnable under certain distributions.  ...  U-learnability has as special cases PAC and Natarajan's model of speed-up learning.  ...  Acknowledgements The author would like to thank David Page and Ashwin Srinivasan of Oxford University Computing Laboratory and Michael Sternberg and Ross King of Imperial Cancer Research Fund for discussions  ... 
doi:10.1016/b978-1-55860-335-6.50052-0 dblp:conf/icml/Muggleton94 fatcat:55iza3henjff7bdeqvprl7txue

Page 5656 of Mathematical Reviews Vol. , Issue 91J [page]

1991 Mathematical Reviews  
A notion of strong learnability is introduced and the classes of learnable and strongly learnable Boolean functions are charac- terized.  ...  On the other hand, we realize a wide class of learnable concepts, and we revisit the no- tion of an almost perfect hypothesis, which relaxes the conditions for learnability.”  ... 

Inductive logic programming

Stephen Muggleton
1994 ACM SIGART Bulletin  
Acknowledgements The author would like to thank David Page and Ashwin Srinivasan of Oxford University Computing Laboratory and Michael Sternberg and Ross King of Imperial Cancer Research Fund for discussions  ...  Example 8 Time-bounded logic programs are U-learnable under DEh.  ...  The descriptions of these patterns are as follows. 1) Almost half of all mutagenic molecules contain 3 fused benzyl rings.  ... 
doi:10.1145/181668.181671 fatcat:ferdi6zdozcctmz3vbscgpckhm

Bayesian inductive logic programming

Stephen Muggleton
1994 Proceedings of the seventh annual conference on Computational learning theory - COLT '94  
Acknowledgements The author would like to thank David Page and Ashwin Srinivasan of Oxford University Computing Laboratory and Michael Sternberg and Ross King of Imperial Cancer Research Fund for discussions  ...  Example 8 Time-bounded logic programs are U-learnable under DEh.  ...  The descriptions of these patterns are as follows. 1) Almost half of all mutagenic molecules contain 3 fused benzyl rings.  ... 
doi:10.1145/180139.178095 dblp:conf/colt/Muggleton94 fatcat:6667u33l7fazfkdl3w76v3ot2i

Learnability of type-logical grammars

Sean A. Fulop
2004 Electronical Notes in Theoretical Computer Science  
It is informally argued that, given the right type logic, the learnable classes of grammars include members which generate natural languages, and thus that natural languages are learnable in this way.  ...  This paper proceeds according to the following: • Type-logical grammar as a framework for syntactic description is briefly summarized.  ...  No class of type-logical languages that does not meet this condition is learnable by the above discovery procedure.  ... 
doi:10.1016/s1571-0661(05)82577-0 fatcat:zfz2fsw6crhsvovybnrwfguqka

Learnability of Type-logical Grammars

Sean A. Fulop
2007 Research on Language and Computation  
It is informally argued that, given the right type logic, the learnable classes of grammars include members which generate natural languages, and thus that natural languages are learnable in this way.  ...  This paper proceeds according to the following: • Type-logical grammar as a framework for syntactic description is briefly summarized.  ...  No class of type-logical languages that does not meet this condition is learnable by the above discovery procedure.  ... 
doi:10.1007/s11168-007-9026-2 fatcat:ujxzoneuoreipb2kwfl2kvstqq

(Agnostic) PAC Learning Concepts in Higher-Order Logic [chapter]

K. S. Ng
2006 Lecture Notes in Computer Science  
This paper studies the PAC and agnostic PAC learnability of some standard function classes in the learning in higher-order logic setting introduced by Lloyd et al.  ...  Our satisfyingly simple analysis provides another case for a more in-depth study and wider uptake of the proposed higher-order logic approach to symbolic machine learning.  ...  It is similar in design to Cohen's antecedent description grammars [4] . We give an informal description of it now.  ... 
doi:10.1007/11871842_71 fatcat:b2yaqxw2zbdtffe7prqperente

Learnability of constrained logic programs [chapter]

Sašo Džeroski, Stephen Muggleton, Stuart Russell
1993 Lecture Notes in Computer Science  
We then derive some positive results concerning the learnability of these restricted classes of logic programs, by reduction to a standard propositional learning problem.  ...  The field of Inductive Logic Programming (ILP) is concerned with inducing logic programs from examples in the presence of background knowledge.  ...  Acknowledgements The work reported in this paper is part of the ESPRIT BRA Project 6020 Inductive Logic Programming. Thanks to Luc De Raedt for his comments on the paper.  ... 
doi:10.1007/3-540-56602-3_148 fatcat:yjwrdw5hvjcbzo6fkspjq6dhcu

The probabilistic analysis of language acquisition: Theoretical, computational, and experimental analysis [article]

Anne S. Hsu, Nick Chater (Univ. College, University London), Paul M.B. Vitanyi
2010 arXiv   pre-print
In previous work, this framework was used to make learnability predictions for a wide variety of linguistic constructions, for which learnability has been much debated.  ...  languages, purely from observing samples of the language.  ...  When using this framework to analyze learnability of a linguistic construction, there are two main assumptions: 1) The description of the grammatical rule for the construction to be learned. 2) The choice  ... 
arXiv:1006.3271v1 fatcat:3bijjucru5af7kq7bcdo2soaqu
« Previous Showing results 1 — 15 out of 9,125 results