Abstract
Convergent realists desire scientific methods that converge reliably to informative, true theories over a wide range of theoretical possibilities. Much attention has been paid to the problem of induction from quantifier-free data. In this paper, we employ the techniques of formal learning theory and model theory to explore the reliable inference of theories from data containing alternating quantifiers. We obtain a hierarchy of inductive problems depending on the quantifier prefix complexity of the formulas that constitute the data, and we provide bounds relating the quantifier prefix complexity of the data to the quantifier prefix complexity of the theories that can be reliably inferred from such data without background knowledge. We also examine the question whether there are theories with mixed quantifiers that can be reliably inferred with closed, universal formulas in the data, but not without.
Similar content being viewed by others
References
Lenore and Manuel Blum. Towards a Mathematical Theory of Inductive Inference. Information and Control 28: 125–55, June 1975.
J. Case and C. Smith. Anomaly Hierarchies of Mechanized Inductive Inference. In Proceedings of the Tenth ACM Symp. on Theory of Computing, pages 314–319. 1978.
C. C. Chang and H. J. Keisler, Model Theory. North-Holland, Amsterdam, 1973.
Haim Gaifman and Marc Snir. Probabilities over Rich Languages, Testing and Randomness. Journal of Symbolic Logic 47: 495–548, 1982.
Clark Glymour. Inductive Inference in the Limit. Erkenntnis 2: 23–31, 1985.
David Haussler. Bias, Version Spaces and Valiant's Learning Framework. In Proceedings of the Fourth International Workshop on Learning, pages 324–334. Morgan Kaufmann, Los Altos, Ca., 1987.
M. Kearns, M. Li, L. Pitt, and L. Valiant. Recent Results on Boolean Concept Learning. In Proceedings of the Fourth International Workshop on Learning, pages 337–352. Morgan Kaufmann, Los Altos, Ca., 1987.
Kevin T.Kelly and Clark Glymour. Convergence to the Truth and Nothing But the Truth. Philosophy of Science 56: 1989.
Osherson, D. and Weinstein, S.. Identification in the Limit of First Order Structures. Journal of Philosophical Logic 15: 55–81, 1986.
Osherson, D., Stob, M., and Weinstein, S.. Systems that Learn. M.I.T. Press, Cambridge, Mass., 1986.
Osherson, D. and Weinstein, S. Paradigms of Truth Detection. Journal of Philosophical Logic 18: 1–42, 1989.
L. Pitt and L. G. Valiant. Computational Limitations on Learning from Examples. Technical Report TR-05-86, Center for Research in Computing Technology, 1986.
Ehud Y. Shapiro. Inductive Inference of Theories from Facts. Research Report 192, Yale University: Department of Computer Science, February, 1981.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Kelly, K.T., Glymour, C. Theory discovery from data with mixed quantifiers. J Philos Logic 19, 1–33 (1990). https://doi.org/10.1007/BF00211184
Issue Date:
DOI: https://doi.org/10.1007/BF00211184