Abstract
A default theory can sanction different, mutually incompatible, answers to certain queries. We can identify each such theory with a set of related credulous theories, each of which produces but a single response to each query, by imposing a total ordering on the defaults. Our goal is to identify the credulous theory with optimal “expected accuracy” averaged over the natural distribution of queries in the domain. There are two obvious complications: First, the expected accuracy of a theory depends on the query distribution, which is usually not known. Second, the task of identifying the optimal theory, even given that distribution information, is intractable. This paper presents a method, OptAcc, that side-steps these problems by using a set of samples to estimate the unknown distribution, and by hill-climbing to a local optimum. In particular, given any error and confidence parameters ε, δ > 0, OptAcc produces a theory whose expected accuracy is, with probability at least 1−δ, within ε of a local optimum.
Preview
Unable to display preview. Download preview PDF.
References
Carlos E. Alchourrón, Peter Gärdenfors, and David Makinson. On the logic of theory change: Partial meet contraction and revision functions. Journal of Symbolic Logic, 50:510–30, 1985.
Mark Boddy and Thomas Dean. Solving time dependent planning problems. Technical report, Brown University, 1988.
Alex Borgida and David Etherington. Hierarchical knowledge bases and efficient disjunctive reasoning. In Proceedings of KR-89, pages 33–43, Toronto, May 1989.
Bruce G. Buchanan, Thomas M. Mitchell, Reid G. Smith, and C. R. Johnson, Jr. Models of learning systems. In Encyclopedia of Computer Science and Technology, volume 11. Dekker, 1978.
B. Bollobás. Random Graphs. Academic Press, 1985.
Gerhard Brewka. Preferred subtheories: An extended logical framework for default reasoning. In Proceedings of IJCAI-89, pages 1043–48, Detroit, August 1989.
K. Clark. Negation as failure. In H. Gallaire and J. Minker, editors, Logic and Data Bases, pages 293–322. Plenum Press, New York, 1978.
William W. Cohen. Learning from textbook knowledge: A case study. In Proceeding of AAAI-90, 1990.
William W. Cohen. Abductive explanation-based learning: A solution to the multiple inconsistent explanation problems. Machine Learning, 8(2):167–219, March 1992.
Thomas Dean and Mark Boddy. An analysis of time-dependent planning. In Proceedings of AAAI-88, pages 49–54, August 1988.
Mukesh Dalal and David Etherington. Tractable approximate deduction using limited vocabulary. In Proceedings of CSCSI-92, Vancouver, May 1992.
Jon Doyle and Ramesh Patil. Two theses of knowledge representation: Language restrictions, taxonomic classification, and the utility of representation services. Artificial Intelligence, 48(3), 1991.
N. Flann and T. G. Dietterich. A study of explanation-based methods for inductive learning. Machine Learning, 4, 1989.
Peter Gardenfors. Knowledge in Flux: Modeling the Dynamics of the Epistemic States. Bradford Book, MIT Press, Cambridge, MA, 1988.
Russell Greiner and Charles Elkan. Measuring and improving the effectiveness of representations. In Proceedings of IJCAI-91, pages 518–24, Sydney, Australia, August 1991.
Russell Greiner and Igor Jurišica. A statistical approach to solving the EBL utility problem. In Proceedings of AAAI-92, San Jose, 1992.
Russell Greiner and Pekka Orponen. Probably approximately optimal derivation strategies. In J.A. Allen, R. Fikes, and E. Sandewall, editors, Proceedings of KR-91, San Mateo, CA, April 1991. Morgan Kaufmann.
Russell Greiner. Learning near optimal horn approximations. In Proceedings of Knowledge Assimilation Symposium, Stanford, March 1992.
Russell Greiner. Probabilistic hill-climbing: Theory and applications. In Proceedings of CSCSI-92, Vancouver, June 1992.
Russell Greiner. The complexity of computing optimally-accurate default theories. Technical report, Siemens Corporate Research, 1993.
Benjamin Grosof. Generalizing prioritization. In Proceedings of KR-91, pages 289–300, Boston, April 1991.
Russell Greiner and Dale Schuurmans. Learning useful horn approximations. In B. Nebel, C. Rich, and W. Swartout, editors, Proceedings of KR-92, San Mateo, CA, October 1992. Morgan Kaufmann.
David Haussler. Quantifying inductive bias: AI learning algorithms and Valiant's learning framework. Artificial Intelligence, pages 177–221, 1988.
Geoff Hinton. Connectionist learning procedures. Artificial Intelligence, 40(1–3):185–234, September 1989.
David Haussler and Leslie Valiant, editors. Proceedings of the First Workshop on Computational Learning Theory. Morgan Kaufmann, MIT, 1988.
H. Kyburg. The reference class. Philosophy of Science, 50, 1982.
Hector J. Levesque. Foundations of a functional approach to knowledge representation. Artificial Intelligence, 23:155–212, 1984.
R. Loui. Computing reference classes. In AAAI Workshop on Uncertainty. Morgan Kaufmann, St Paul, 1988.
S. Muggleton and W. Buntine. Machine invention of first order predicates by inverting resolution. In Proceedings of IML-88, pages 339–51. Morgan Kaufmann, 1988.
Ryszard S. Michalski, Jaime G. Carbonell, and Thomas M. Mitchell, editors. Machine Learning: An Artificial Intelligence Approach. Tioga Publishing Company, Palo Alto, CA, 1983.
Thomas M. Mitchell. The need for bias in learning generalizations. Technical Report CBM-TR-117, Laboratory for Computer Science Research, May 1980.
Paul Morris. Curing anomalous extensions. In Proceedings of AAAI-87, pages 437–42, Seattle, July 1987.
Pekka Orponen and Russell Greiner. On the sample complexity of finding good search strategies. In Proceedings of COLT-90, pages 352–58, Rochester, August 1990.
Dirk Ourston and Raymond J. Mooney. Changing the rules: A comprehensive approach to theory refinement. In Proceedings of AAAI-90, pages 815–20, 1990.
M. Pazzani. Selecting the best explanation in explanation-based learning. In Proceedings of Symposium on Explanation-Based Learning, Stanford, March 1988.
David Poole, Randy Goebel, and Romas Aleliunas. Theorist: A logical reasoning system for default and diagnosis. Technical Report CS-86-06, Logic Programming and Artificial Intelligence Group, Faculty of Mathematics, University of Waterloo, February 1986.
J. Ross Quinlan. Learning logical definitions from relations. Machine Learning Journal, 5(3):239–66, August 1990.
Raymond Reiter. Nonmonotonic reasoning. In Annual Review of Computing Sciences, volume 2, pages 147–87. Annual Reviews Incorporated, Palo Alto, 1987.
Stuart J. Russell and Benjamin N. Grosof. A declarative approach to bias in concept learning. In Proceedings of AAAI-87, pages 505–10, Seattle, WA, July 1987.
Ehud Shapiro. Algorithmic Program Debugging. MIT Press, 1983.
Lokendra Shastri. Default reasoning in semantic networks: A formalization of recognition and inheritance. Artificial Intelligence, 39:283–355, 1989.
Bart Selman and Henry Kautz. Knowledge compilation using horn approximations. In Proceedings of AAAI-91, pages 904–09, Anaheim, August 1991.
Paul van Arragon. Nested default reasoning with priority levels. In Proceedings of CSCSI-90, pages 77–83, Ottawa, May 1990.
David Vormittag. Evaluating answers to questions, May 1991. Bachelors Thesis, University of Toronto.
Jonathan Wong. Improving the accuracy of a representational system, May 1991. Bachelors Thesis, University of Toronto.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1994 Springer-Verlag Berlin Heidelberg
About this chapter
Cite this chapter
Greiner, R., Schuurmans, D. (1994). Learning an optimally accurate representation system. In: Lakemeyer, G., Nebel, B. (eds) Foundations of Knowledge Representation and Reasoning. Lecture Notes in Computer Science, vol 810. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-58107-3_9
Download citation
DOI: https://doi.org/10.1007/3-540-58107-3_9
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-58107-9
Online ISBN: 978-3-540-48453-0
eBook Packages: Springer Book Archive