Abstract
In this paper, we study exact learning of logic programs from entailment and present a polynomial time algorithm to learn a rich class of logic programs that allow local variables and include many standard programs like append, merge, split, delete, member, prefix, suffix, length, reverse, append/4 on lists, tree traversal programs on binary trees and addition, multiplication, exponentiation on natural numbers. Grafting a few aspects of incremental learning [9] onto the framework of learning from entailment [3], we generalize the existing results to allow local variables, which play an important role of sideways information passing in the paradigm of logic programming.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
D. Angluin (1988), Learning with hints, Proc. COLT’88, pp. 223–237.
D. Angluin (1988), Queries and concept learning, Machine Learning 2, pp. 319–342.
H. Arimura (1997), Learning acyclic first-order Horn sentences from entailment, Proc. ALT’97, Lecture Notes in Artificial intelligence 1316, pp. 432–445.
W. Cohen and H. Hirsh (1992), Learnability of description logics, Proc. COLT’92, pp. 116–127.
S. Dzeroski, S. Muggleton and S. Russel (1992), PAC-learnability of determinate logic programs, Proc. of COLT’92, pp. 128–135.
M. Frazier and L. Pitt (1993), Learning from entailment: an application to propositional Horn sentences, Proc. ICML’93, pp. 120–127.
M. Frazier and L. Pitt (1994), CLASSIC learning, Proc. COLT’94, pp. 23–34.
P. Idestam-Almquist (1996), Efficient induction of recursive definitions by structural analysis of saturations, pp. 192–205 in L. De Raedt (ed.), Advances in inductive logic programming, IOS Press.
M.R.K. Krishna Rao (1995), Incremental Learning of Logic Programs, Proc. of Algorithmic Learning Theory, ALT’95, LNCS 997, pp. 95–109. Revised version in Theoretical Computer Science special issue on ALT’95, Vol 185, 193–213.
J. W. Lloyd (1987), Foundations of Logic Programming, Springer-Verlag.
S. Muggleton and L. De Raedt (1994), Inductive logic programming: theory and methods, J. Logic Prog. 19/20, pp. 629–679.
S.H. Nienhuys-Cheng and R. de Wolf (1995), The subsumption theorem for several forms of resolution, Tech. Rep. EUR-FEW-CS-96-14, Erasmus University, Rotterdam.
C.D. Page and A.M. Frish (1992), Generalization and learnability: a study of constrained atoms, in Muggleton (ed.) Inductive Logic programming, pp. 29–61.
C. Reddy and P. Tadepalli (1998), Learning first order acyclic Horn programs from entailment, to appear in Proc. of International Conference on Machine Learning, ICML’98.
C. Rouveirol (1992), Extensions of inversion of resolution applied to theory completion, in Muggleton (ed.) Inductive Logic programming, pp. 63–92.
E. Shapiro (1981), Inductive inference of theories from facts, Tech. Rep., Yale Univ.
E. Shapiro (1983), Algorithmic Program Debugging, MIT Press.
L. Sterling and E. Shapiro (1994), The Art of Prolog, MIT Press.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1998 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Krishna Rao, M.R.K., Sattar, A. (1998). Learning from Entailment of Logic Programs with Local Variables. In: Richter, M.M., Smith, C.H., Wiehagen, R., Zeugmann, T. (eds) Algorithmic Learning Theory. ALT 1998. Lecture Notes in Computer Science(), vol 1501. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-49730-7_11
Download citation
DOI: https://doi.org/10.1007/3-540-49730-7_11
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-65013-3
Online ISBN: 978-3-540-49730-1
eBook Packages: Springer Book Archive