Abstract
We extend Valiant's model to learn concepts defined by a subset of predicate logic. The results in this paper parallel those of D.Hasusser, but the restrictions implying these results go in different directions.
This work was supported by National Sciences Foundation of China under Grant 6907330
This is a preview of subscription content, log in via an institution.
Preview
Unable to display preview. Download preview PDF.
References
Blumer, A., Ehrenfeucht, A., Haussler, D., Warmuth, M. (1987) Occam's Razor. Infor. Process. Lett. 24, 377–380.
Cohen,W.W & Hirsh,H. Learnability of Description Logics. COLT'92, 116–127
Dietterich,T.G & Michalski,R.S. (1983) A Comparetive Review of Selected Methods for Learning from Examples. in Machine Learning An Artificial Intelligence Approach. Ed. by Michalski,R.S. & Carbonell,J,G.
Garey, M. & Johnson, D. (1979) Computers and Intractablity A Guide to the theory of NP-completeness.
Haussler, D. (1988) Quantifying Inductive Bias: AI Learning Algorithms and Valiant's Model. Artif. Intell. 36, 177–221.
Haussler, D. (1988) Learning Conjuncctive Concepts in Structural Domains. Tech Report UCSC-CRL-88-39
Kearns, M. Li, M. Laliant, L. Recent Results on Boolean concept Learning Proc. 4th Inter. Workshop on Machine Learning 267–280.
Mehlhorn, K (1984) Data Structures and Algorithms. vol.2: Graph Algorithms and NP-Complteness.
Pitt, L. Valiant, L.G. (1988) Computational Limitations on Learning from Examples. JACM Vol 85. No.4 Oct. 1988 965–984.
Valiant, L. G. (1984) A theory of the learnable. Comm. ACM, 27, No.11, 1134–1142.
Vere,S.A. (1975) Induction of Concepts in the Predicate Calculus. Proc. 4th IJCAI 281–287. Tbilisi, USSR.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1993 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Yin, J., Hong, Z. (1993). On the learnability of a restricted predicate formulae. In: Ésik, Z. (eds) Fundamentals of Computation Theory. FCT 1993. Lecture Notes in Computer Science, vol 710. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-57163-9_40
Download citation
DOI: https://doi.org/10.1007/3-540-57163-9_40
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-57163-6
Online ISBN: 978-3-540-47923-9
eBook Packages: Springer Book Archive