Abstract
We consider inductive logic programming guided by a language bias called abstraction schemata which enables us to specify a partial structure for a target program. Specifically, to improve the efficiency of such learning, we discuss a class of programs for which it is possible to devise a learning algorithm capable of identifying and pruning unpromising uses of the schemata. This identification process includes the bias shift problem: how to decide whether a hypothesis space contains no correct program with respect to a given example specification. For solving this problem, a required property of hypothesis spaces is discovered. This result yields a class of programs that are beyond the representational capabilities of previous approaches — most notably, non-trivial programs with local variables.
This is a preview of subscription content, log in via an institution to check access.
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
H. Ade. Declarative bias for specific-to-general Up systems. Machine Learning, 20:119–154,1995.
J-U.Kietz and S. Wrobel. Controlling the complexity of learning in logic through syntactic and task-oriented models. Inductive Logic Programming, pages 335–359. ACADEMIC PRESS, 1992.
Y. Mukouchi and S. Arikawa. Towards a mathematical theory of machine discovery from facts. Theoretical Computer Science, 137:53–84, 1995.
D.A. Plaisted. Theorem proving with abstraction. Artificial Intelligence, 16:47–108, 1981.
L.D. Raedt and M. Bruynooghe. Interactive concept-learning and constructive induction by analogy. Machine Learning, 8:107–150, 1992.
M.R.K. Krishna Rao. A class of prolog programs inferable from positive data. LNAI 1160, pages 272–284. Springer-Verlag, 1996.
K. Sadohara. A study on analogical logic program synthesis from examples. PhD thesis, Tokyo Institute of Technology, 1996.
K. Sadohara and M. Haraguchi. Analogical logic program synthesis algorithm that can refute inappropriate similarities. LNAI 997, pages 266–281. Springer-Verlag, 1995.
S. Sakurai and M. Haraguchi. Towards learning by abstraction. Proc. 2nd Workshop on Algorithmic Learning Theory, pages 288–298, 1991.
E.Y. Shapiro. Inductive inference of theories from facts. Technical Report 192, Yale University Computer Science Dept., 1981.
T. Shinohara. Inductive inference of monotonic formal systems from positive data. New Generation Computing, 8:371–384, 1991.
I. Stahl. The appropriateness of predicate invention as bias shift operation in ilp. Machine Learning, 20:95–117, 1995.
B. Tausend and S. Bell. Analogical reasoning for logic programming. Inductive Logic Programming, pages 397–408. ACADEMIC PRESS, 1992.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1997 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Sadohar, K., Haraguchi, M. (1997). Using abstraction schemata in inductive logic programming. In: Lavrač, N., Džeroski, S. (eds) Inductive Logic Programming. ILP 1997. Lecture Notes in Computer Science, vol 1297. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3540635149_54
Download citation
DOI: https://doi.org/10.1007/3540635149_54
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-63514-7
Online ISBN: 978-3-540-69587-5
eBook Packages: Springer Book Archive