Abstract
This paper formalizes a new learning-from-examples problem: identifying a correct concept definition from positive examples such that the concept is some specialization of a target concept defined by a domain theory. It describes an empirical study that evaluates three methods for solving this problem: explanation-based generalization (EBG), multiple example explanation-based generalization (mEBG), and a new method, induction over explanations (IOE). The study demonstrates that the two existing methods (EBG and mEBG) exhibit two shortcomings: (a) they rarely identify the correct definition, and (b) they are brittle in that their success depends greatly on the choice of encoding of the domain theory rules. The study demonstrates that the new method, IOE, does not exhibit these shortcomings. This method applies the domain theory to construct explanations from multiple training examples as in mEBG, but forms the concept definition by employing a similarity-based generalization policy over the explanations. IOE has the advantage that an explicit domain theory can be exploited to aid the learning process, the dependence on the initial encoding of the domain theory is significantly reduced, and the correct concepts can be learned from few examples. The study evaluates the methods in the context of an implemented system, called Wyl2, which learns a variety of concepts in chess including “skewer” and “knight-fork.”
Article PDF
Similar content being viewed by others
References
Bennett, J.S. and Dietterich, T.G. (1986). The test incorporation hypothesis and the weak methods (Technical Report No. 86-30-4). Corvallis: Oregon State University, Department of Computer Science.
Cheeseman, P., Kelly, J., Self, M., Strutz, J., Taylor, W., and Freeman, D. (1988). AutoClass: A Bayesian classification system. Proceedings of the Fifth International Conference on Machine Learning (pp. 54–64). Ann Arbor, MI: Morgan Kaufmann.
Cohen, W. (1988). Generalizing number and learning from multiple examples in explanation based learning. Proceedings of the Fifth International Conference on Machine Learning (pp. 256–269). Ann Arbor, MI: Morgan Kaufmann.
DeJong, G., and Mooney, R. (1986). Explanation-based learning: An alternative view. Machine Learning, 1, 145–176.
Dietterich, T.G. (1986). Learning at the knowledge level. Machine Learning, 1, 287–316.
Dietterich, T.G., London, B., Clarkson, K., and Dromey, G. (1982). Learning and inductive inference. In PR. Cohen and E. A. Feigenbaum (Eds.), The handbook of artificial intelligence (Vol. 3). San Mateo, CA: Morgan Kaufmann.
Drastal, G., Raatz, S. and Czako, G. (1989). Induction in an abstract space: A form of constructive induction. Proceedings of the Eleventh International Joint Conference on Artificial Intelligence. Detroit, MI: Morgan Kaufmann.
Ehrenfeucht, A., Haussler, D., Kearns, M., and Valiant, L. (1988). A general lower bound on the number of examples needed for learning. COLT 88: Proceedings of the 1988 Workshop on Computational Learning Theory (pp. 139–154). Cambridge, MA.
Flann, N.S. (1988). Improving problem solving performance by example guided reformulation of knowledge. Proceedings of the First International Workshop on Change of Representation and Inductive Bias (pp 14–34). Briarcliff, NY.
Flann, N.S. (1989). Notes on Wyl2: Implementing and using universal quantification in an explanation-based learning system (Technical Report). Corvallis: Oregon State University, Department of Computer Science.
Genesereth, M.R., and Nilsson, NJ. (1987). The logical foundations of artificial intelligence. San Mateo, CA: Morgan Kaufmann.
Gupta, A. (1988). Significance of the explanation language in EBL. Proceedings of the AAAl Spring Symposium on Explanation-Based Learning (pp. 73–77). Stanford University: AAAI.
Haussler, D. (1988). Quantifying inductive bias: AI learning algorithms and Valiant's learning framework. Artificial Intelligence, 36, 177–222.
Hirsh, H. (1987). Explanation-based generalization in a logic-programming environment. Proceedings of the Tenth International Joint Conference on Artificial Intelligence (pp. 221–227). Milan, Italy: Morgan Kaufmann.
Hirsh, H. (1988). Knowledge as bias. Proceedings of the First International Workshop on Change of Representation and Inductive Bias (pp. 186–192). Briarcliff, NY.
Kedar-Cabelli, S.T. (1985). Purpose-directed analogy: A summary of current research. Proceedings of the Third International Conference on Machine Learning (pp. 80–83). Skytop, PA.
Kedar-Cabelli, S.T., and McCarty, L.T. (1987). Explanation-based generalization as resolution theorem proving. Proceedings of the Fourth International Workshop on Machine Learning (pp. 383–389). Irvine, CA: Morgan Kaufmann.
Laird, J.E. (1986). SOAR user's manual. (Technical Report). Palo Alto, CA: Xerox Palo Alto Research Center.
Laird, J.E., Rosenbloom, P.S., and Newell, A. (1986). Chunking in SOAR: The anatomy of a general learning mechanism. Machine Learning, 1, 47–80.
Michalski, R.S. (1983). A theory and methodology of inductive learning. In R.S. Michalski, J.G. Carbonell and T.M. Mitchell (Eds.), Machine learning: An artificial intelligence approach. San Mateo, CA: Morgan Kaufmann.
Minton, S. (1988). Learning efficient search control knowledge: An explanation-based approach. Doctoral dissertation, Computer Science Department, Carnegie Mellon University, Pittsburgh, PA.
Mitchell, T.M. (1982). Generalization as search. Artificial Intelligence, 18, 203–226.
Mitchell, T.M. (1983). Learning and problem solving. Proceedings of the Eighth International Joint Conference on Artificial Intelligence (pp. 1139–1151). Karlsruhe, West Germany: Morgan Kaufmann.
Mitchell, T.M., Utgoff, P. and Banerji, R. (1983). Learning by experimentation: Acquiring and refining problemsolving heuristics. In R.S. Michalski, J.G. Carbonell and T.M. Mitchell (Eds.), Machine Learning: An artificial intelligence approach. San Mateo, CA: Morgan Kaufmann.
Mitchell, T., Keller, R., and Kedar-Cabelli, S. (1986). Explanation-based generalization: A unifying view. Machine Learning, 1, 47–80.
Mooney, R.J., and Bennett, S.W. (1986). A domain independent explanation-based generalizer. Proceedings of the Fifth National Conference on Artificial Intelligence (pp. 551–555). Philadelphia, PA: Morgan Kaufmann.
Morrison, S. (1968). Chess: A beginner's guide. Old Tappan, NJ: Newitt House.
Pazzani, M.J. (1988). Learning causal relationships: An integration of empirical and explanation based learning methods. Doctoral dissertation, Computer Science Department, University of California, Los Angeles, CA.
Plotkin, G.D. (1970). A note on inductive generalization. In B. Meltzer and D. Michie (Eds.), Machine intelligence (Vol. 5). New York: American Elsevier.
Prieditis, A.E. (1988). Environment-guided program transformation. Proceedings of the AAA1 Spring Symposium on Explanation-Based Learning (pp. 201–210). Stanford University: AAAI.
Quinlan, J.R. (1982). Semi-autonomous acquisition of pattern-based knowledge. In J.E. Hayes and D. Michie (Eds.), Machine intelligence (Vol. 10). New York: John Wiley & Sons.
Quinlan, J.R. (1983). Learning efficient classification procedures and their application to chess end games. In R.S. Michalski, J.G. Carbonnell and T.M. Mitchell (Eds.), Machine learning: An artificial intelligence approach San Mateo, CA: Morgan Kaufmann.
Russell, S. (1985). The compleat guide to MRS. (Technical Report No. KSL-85-13). Palo Alto, CA: Stanford University, Department of Computer Science, Knowledge Systems Laboratory.
Schlimmer, J. (1987). Learning and representation change. Proceedings of the Sixth National Conference on Artificial Intelligence (pp. 511–515). Seattle, WA: Morgan Kaufmann.
Seshu, R., Rendell, L., and Tcheng, D. (1988). Managing constructive induction using subcomponent assessment and multiple-objective optimization. Proceedings of the First International Workshop on Change of Representation and Inductive Bias (pp. 293–305). Briarcliff, NY.
Shavlik, J., and DeJong, G. (1987). An explanation-based approach to generalizing number. Proceedings of the Tenth International Joint Conference on Artificial Intelligence (pp. 236–238). Milan, Italy: Morgan Kaufmann.
Spiegel, R. (1975). Schaum's outline series: Theory and problems of probability and statistics. McGraw-Hill.
Tadepalli, P. (1989). Lazy explanation-based learning: A solution to the intractable theory problem. Proceedings of the Eleventh International Joint Conference on Artificial Intelligence. Detroit, MI: Morgan Kaufmann.
Utgoff, P.E. (1986). A shift in bias for inductive concept learning. In R.S. Michalski, J.G. Carbonell and T.M. Mitchell (Eds.), Machine learning: An artificial intelligence approach (Vol 2). San Mateo, CA: Morgan Kaufmann.
Van Harmelen, F., and Bundy, A. (1988). Explanation based generalization = partial evaluation. Artificial Intelligence, 36, 401–412.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Flann, N.S., Dietterich, T.G. A Study of Explanation-Based Methods for Inductive Learning. Machine Learning 4, 187–226 (1989). https://doi.org/10.1023/A:1022652016863
Issue Date:
DOI: https://doi.org/10.1023/A:1022652016863