Abstract
Consider an agent (or expert system) with a knowledge base KB that includes statistical information (such as “90% of patients with jaundice have hepatitis”), first-order information (“all patients with hepatitis have jaundice”), and default information (“patients with jaundice typically have a fever”). A doctor with such a KB may want to assign a degree of belief to an assertion ϕ such as “Eric has hepatitis”. Since the actions the doctor takes may depend crucially on this degree of belief, we would like to specify a mechanism by which she can use her knowledge base to assign a degree of belief to ϕ in a principled manner. We have been investigating a number of techniques for doing so; in this paper we give an overview of one of them. The method, which we call the random worlds method, is a natural one: For any given domain size N, we consider the fraction of models satisfying ϕ among models of size N satisfying KB. If we do not know the domain size N, but know that it is large, we can approximate the degree of belief in ϕ given KB by taking the limit of this fraction as N goes to infinity. As we show, this approach has many desirable features. In particular, in many cases that arise in practice, the answers we get using this method provably match heuristic assumptions made in many standard AI systems.
The work of Fahiem Bacchus was supported by NSERC under their operating grants program and by IRIS. The work of Adam Grove, Joseph Halpern, and Daphne Koller was sponsored in part by the Air Force Office of Scientific Research (AFSC), under Contract F49620-91-C-0080. During this work, Grove was at Stanford University, and was supported by an IBM Graduate Fellowship. The United States Government is authorized to reproduce and distribute reprints for governmental purposes.
Preview
Unable to display preview. Download preview PDF.
References
F. Bacchus. Representing and Reasoning with Probabilistic Knowledge. MIT Press, Cambridge, MA, 1990.
F. Bacchus, A. J. Grove, J. Y. Halpern, and D. Koller. From statistics to belief. In Proc. National Conference on Artificial Intelligence (AAAI '92), pages 602–608, 1992.
F. Bacchus, A. J. Grove, J. Y. Halpern, and D. Koller. Generating degrees of belief from statistical information. In preparation, 1993.
F. Bacchus, A. J. Grove, J. Y. Halpern, and D. Koller. Statistical foundations for default reasoning. In Proc. Thirteenth International Joint Conference on Artificial Intelligence (IJCAI '93), 1993.
R. Carnap. Logical Foundations of Probability. University of Chicago Press, Chicago, 1950.
R. Carnap. The Continuum of Inductive Methods. University of Chicago Press, Chicago, 1952.
A. J. Grove, J. Y. Halpern, and D. Koller. Asymptotic conditional probabilities for first-order logic. In Proc. 24th ACM Symp. on Theory of Computing, pages 294–305, 1992.
A. J. Grove, J. Y. Halpern, and D. Koller. Random worlds and maximum entropy. In Proc. 7th IEEE Symp. on Logic in Computer Science, pages 22–33, 1992.
I. Hacking. The Emergence of Probability. Cambridge University Press, Cambridge, UK, 1975.
E. T. Jaynes. Where do we stand on maximum entropy? In R. D. Levine and M. Tribus, editors, The Maximum Entropy Formalism, pages 15–118. MIT Press, Cambridge, MA, 1978.
W. E. Johnson. Probability: The deductive and inductive problems. Mind, 41(164):409–423, 1932.
J. M. Keynes. A Treatise on Probability. Macmillan, London, 1921.
D. Koller and J. Y. Halpern. A logic for approximate reasoning. In B. Nebel, C. Rich, and W. Swartout, editors, Proc. Third International Conference on Principles of Knowledge Representation and Reasoning (KR '92), pages 153–164, 1992.
S. Kraus, D. Lehmann, and M. Magidor. Nonmonotonic reasoning, preferential models and cumulative logics. Artificial Intelligence, 44:167–207, 1990.
J. von Kries. Die Principien der Wahrscheinlichkeitsrechnung und Rational Expectation. Freiburg, 1886.
D. Lehmann. What does a conditional knowledge base entail? In Proc. First International Conference on Principles of Knowledge Representation and Reasoning (KR '89), pages 212–222, 1989.
N. Nilsson. Probabilistic logic. Artificial Intelligence, 28:71–87, 1986.
J. Pearl. Probabilistic semantics for nonmonotonic reasoning: A survey. In R. J. Brachman, H. J. Levesque, and R. Reiter, editors, Proc. First International Conference on Principles of Knowledge Representation and Reasoning (KR '89), pages 505–516, 1989. Reprinted in Readings in Uncertain Reasoning, G. Shafer and J. Pearl (eds.), Morgan Kaufmann, San Mateo, CA, 1990, pp. 699–710.
R. Reiter and G. Criscuolo. On interacting defaults. In Proc. Seventh International Joint Conference on Artificial Intelligence (IJCAI '81), pages 270–276, 1981.
G. Shafer. A Mathematical Theory of Evidence. Princeton University Press, Princeton, NJ, 1976.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1993 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Bacchus, F., Grove, A.J., Halpern, J.Y., Koller, D. (1993). Generating degrees of belief from statistical information: An overview. In: Shyamasundar, R.K. (eds) Foundations of Software Technology and Theoretical Computer Science. FSTTCS 1993. Lecture Notes in Computer Science, vol 761. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-57529-4_65
Download citation
DOI: https://doi.org/10.1007/3-540-57529-4_65
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-57529-0
Online ISBN: 978-3-540-48211-6
eBook Packages: Springer Book Archive