Abstract
This paper is concerned with the problem of efficient inductive inference of primitive Prologs from only positive data. The class of primitive Prologs is a proper subclass of one of linear Prologs that is known to be inferable from only positive data. In this paper, we discuss on the consistent and conservative polynomial update time inferability of the subclass. We give a consistent and conservative polynomial update time inference algorithm that, when it is given the base case of the target program as a hint, identifies the subclass in the limit. Furthermore, we give a consistent but not conservative polynomial update time inference algorithm for the subclass using a 2-mmg (minimal multiple generalization) algorithm. The notion of 2-mmg is a natural extension of Plotkin's least generalization. The second inference algorithm uses the 2-mmg algorithm to infer the heads of clauses in a target program.
Preview
Unable to display preview. Download preview PDF.
References
Hiroki Arimura, Hiroki Ishizaka, and Takeshi Shinohara. Polynomial time inference of a subclass of context-free transformations. In Proceedings of 5th Workshop on Computational Learning Theory, 1992.
Hiroki Arimura, Takeshi Shinohara, and Setsuko Otsuki. A polynomial time algorithm for finite unions of tree pattern languages. In Proc. of the 2nd International Workshop on Nonmonotonic and Inductive Logics, 1991. To appear in LNCS.
Hiroki Arimura, Takeshi Shinohara, and Setsuko Otsuki. Polynomial time inference of unions of tree pattern languages. In S. Arikawa, A. Maruoka, and T. Sato, editors, Proc. ALT '91, pp. 105–114. Ohmsha, 1991.
Hiroki Ishizaka. Model inference incorporating generalization. Journal of Information Processing, 11(3):206–211, 1988.
J-L.Lassez, M. J. Maher, and K. Marriott. Unification revisited. In J. Minker, editor, Foundations of Deductive Databases and Logic Programming, pp. 587–625. Morgan Kaufmann, 1988.
John W. Lloyd. Foundations of Logic Programming. Springer-Verlag, 1984.
Stephen Muggleton and Wray Buntine. Machine invention of first-order predicates by inverting resolution. In Proc. 5th International Conference on Machine Learning, pp. 339–352, 1988.
K. Marriott, L. Naish, and J-L. Lassez. Most specific logic programs. In Logic Programming: Proceedings of the Fifth International Conference and Symposium, pp. 910–923. MIT Press, 1988.
Leonard Pitt. Inductive inference, dfas, and computational comlexity. In K. P. Jantke, editor, Proc. AII '89, LNAI 397, pp. 18–44. Springer-Verlag, 1989.
Gordon D. Plotkin. A note on inductive generalization. In B. Meltzer and D. Michie, editors, Machine Intelligence 5, pp. 153–163. Edinburgh University Press, 1970.
Ehud Y. Shapiro. Inductive inference of theories from facts. Technical Report 192, Yale University Computer Science Dept., 1981.
Takeshi Shinohara. Inductive inference of monotonic fomal systems from positive data. In S. Arikawa, S. Goto, S. Ohsuga, and T. Yokomori, editors, Proc. ALT '90, pp. 339–351. Ohmsha, 1990.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1993 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Ishizaka, H., Arimura, H., Shinohara, T. (1993). Efficient inductive inference of primitive Prologs from positive data. In: Doshita, S., Furukawa, K., Jantke, K.P., Nishida, T. (eds) Algorithmic Learning Theory. ALT 1992. Lecture Notes in Computer Science, vol 743. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-57369-0_34
Download citation
DOI: https://doi.org/10.1007/3-540-57369-0_34
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-57369-2
Online ISBN: 978-3-540-48093-8
eBook Packages: Springer Book Archive