Abstract
Knowledge has traditionally been considered to have a beneficial effect on the performance of problem solvers but recent studies indicate that knowledge acquisition is not necessarily a monotonically beneficial process, because additional knowledge sometimes leads to a deterioration in system performance. This paper is concerned with the problem of harmful knowledge: that is, knowledge whose removal would improve a system's performance. In the first part of the paper a unifying framework, called theinformation filtering model, is developed to define the various alternative methods for eliminating such knowledge from a learning system where selection processes, called filters, may be inserted to remove potentially harmful knowledge. These filters are termed selective experience, selective attention, selective acquisition, selective retention, and selective utilization. The framework can be used by developers of learning systems as a guide for selecting an appropriate filter to reduce or eliminate harmful knowledge.
In the second part of the paper, the framework is used to identify a suitable filter for solving a problem caused by the acquisition of harmful knowledge in a learning system calledLassy.Lassy is a system that improves the performance of a PROLOG interpreter by utilizing acquired domain specific knowledge in the form of lemmas stating previously proved results. It is shown that the particular kind of problems that arise with this system are best solved using a novel utilization filter that blocks the use of lemmas in attempts to prove subgoals that have a high probability of failing.
Article PDF
Similar content being viewed by others
References
Aha, D.W., Kibler, D., & Albert, M.K. (1991). Instance-based learning algorithms.Machine Learning, 6 37–66.
Brodie, M.L., & Mattias, J. (1986). On integrating logic programming and databases. In L. Kerschberg (Ed.),Expert database systems. Menlo Park, CA: Benjamin/Cummings.
Buchanan, B.G., & Feigenbaum, E.A. (1982). Foreword. In R. Davis & D.B. Lenat (Eds.),Knowledge based systems in artificial intelligence. New York: McGraw-Hill.
Clark, K.L. & McCabe, F. (1979). The control facilities of ic-prolog. In D. Michie (Ed.),Expert systems in the microelectronic age. Edinburgh, Scotland: University of Edinburgh.
Debray, S.K., & Warren, D.S. (1988). Automatic mode inference for logic programs.The Journal of Logic Programming, 5 207–229.
Dejong, G., & Mooney, R. (1986). Explanation-based learning. An alternative view.Machine Learning, 1 145–176.
Dietterich, T.G., & Michalski, R.S. (1981). Inductive learning of structural description: Evaluation criteria and comparative review of selected method.Artificial Intelligence, 16 257–294.
Etzioni, O. (1988). Hypothesis filtering: A practical approach to reliable learning.Proceedings of The Fifth International Conference on Machine Learning (pp. 416–429). Ann Arbor, MI: Morgan Kaufmann.
Fikes, R.E., Hart, P.E., & Nilsson, N.J. (1972). Learning and executing generalized robot plans.Artificial Intelligence, 3 251–288.
Gallaire, H., & Lasserre, C. (1982). Metalevel control for logic programs. In K.L. Clark & S.A. Tarnlund (Eds.),Logic programming. New York: Academic Press.
Gallaire, H., & Minker, J. (1978).Logic and data bases. New York: Plenum.
Gennari, J.H. (1989). Focused concept formation.Proceedings of The Sixth International Workshop on Machine Learning (pp. 379–382). Ithaca, NY: Morgan Kaufmann.
Holland, J.H. (1975).Adaption in natural and artificial systems. Ann Arbor, MI: University of Michigan Press.
Holland, J.H. (1986). Escaping brittleness: The possibilities of general-purpose learning algorithms applied to parallel rule-based systems. In R.S. Michalski, J.G. Carbonell, & T.M. Mitchell (Eds.),Machine learning: An artificial intelligence approach (vol. 2). Los Altos, CA: Morgan Kaufmann.
Iba, G.A. (1989). A heuristic approach to the discovery of macro-operators.Machine Learning, 3 285–317.
Keller, M.R. (1987). Concept learning in context.Proceedings of Fourth International Workshop on Machine Learning (pp. 482–487). Irvine, CA: Morgan Kaufmann.
Korf, R.E. (1985).Learning to solve problems by searching for macro-operators. Boston: Pitman.
Kowalski, R.A. (1979).Logic for problem solving. New York: Elsevier North Holland.
Kowalski, R.A. (1985). Directions for logic programming.Proceedings of IEEE Symposium On Logic Programming.
Laird, J.E., Rosenbloom, P.S., & Newell, A. (1986). Chunking in soar: The anatomy of a general learning mechanism.Machine Learning, 1 11–46.
Lenat, D.B. (1983). The role of heuristics in learning by discovery: Three case studies. In R.S. Michalski, J.G. Carbonell, & T.M. Mitchell (Eds.),Machine learning: An artificial intelligence appraoch (vol. 1). Palo Alto, CA: Tioga.
Lindsay, R.K., Buchanan, B.G., Feigenbaum, E.H., & Lederberg, J. (1980).Applications of artificial intelligence for organic chemistry: The Dendral project. New York: McGraw-Hill.
Lloyd, J.W. (1984).Foundations of logic programming. New York: Springer-Verlag.
Markovitch, S. (1989).Information filtering: Selection mechanisms in learning systems. Doctoral dissertation, EECS Department, University of Michigan.
Markovitch, S., & Scott, P.D. (1988). The role of forgetting in learning.Proceedings of The Fifth International Conference on Machine Learning (pp. 459–465). Ann Arbor, MI: Morgan Kaufmann.
Markovitch, S., & Scott, P.D. (1989a). Automatic ordering of subgoals—a machine learning approach.Proceedings of North American Conference on Logic Programming (pp. 224–240). Ithaca, NY: MIT Press.
Markovitch, S., & Scott, P.D. (1989b). Post-prolog: Structured partially ordered prolog (TR CMI-89-018) Ann Arbor, MI: Center for Machine Intelligence.
Markovitch, S., & Scott, P.D. (1989c). Utilization filtering: A method for reducing the inherent harmfulness of deductively learned knowledge.Proceedings of The Eleventh International Joint Conference for Artificial Intelligence (pp. 738–743). Detroit, MI: Morgan Kaufmann.
Minton, S. (1985). Selectively generalizing plans for problem solving.Proceedings of The Ninth International Joint Conference on Artificial Intelligence (pp. 596–599). Los Angeles, CA: Morgan Kaufmann.
Minton, S. (1988a).Learning search control knowledge: An explanation-based approach. Boston, MA: Kluwer.
Minton, S. (1988b). Quantitative results concerning the utility of explanation-based learning.Proceedings of Seventh National Conference on Artificial Intelligence (pp. 564–569). Morgan Kaufmann.
Mitchell, T.M. (1982). Generalization as search.Artificial Intelligence, 18 203–226.
Mitchell, T.M., Keller, R.M., & Kedar-Cabelli, S.T. (1986). Explanation-based generalization: A unifying view.Machine Learning, 1 47–80.
Mitchell, T.M., Utgoff, P.E., & Banerji, R. (1983). Learning by experimentation: Acquiring and refining problemsolving heuristics. In R.S. Michalski, J.G. Carbonell, & T.M. Mitchell (Eds.),Machine learning: An artificial intelligence approach. Palo Alto, CA: Tioga.
Mooney, R. (1989). The effect of rule use on the utility of explanation-based learning.Proceedings of The Eleventh International Joint Conference for Artificial Intelligence (pp. 725–730). Detroit, MI: Morgan Kaufmann.
Naish, L. (1985). Automatic control for logic programs.The Journal of Logic Programming, 3 167–183.
Parker, S.D., Carey, M., Golshani, F., Jarke, M., Sciore, E., & Walker, A. (1986). Logic programming and databases.Expert Database Systems—Proceedings from The First International Workshop (pp. 35–48). Menlo Park, CA: Benjamin/Cummings.
Pearl, J. (1984).Heuristics: Intelligent search strategies for computer problem solving. Reading, MA: Addison-Wesley.
Pereira, L.M., & Porto, A. (1982). Selective backtracking. In K.L. Clark & S.A. Tarnlund (Eds.),Logic programming. New York: Academic Press.
Porter, B.W., Bareiss, R., & Holte, R.C. (1990). Concept learning and heuristic classification in weak-theory domains.Artificial Intelligence, 45 229–263.
Prieditis, A.E., & Mostow, J. (1987). Prolearn: Toward a prolog interpreter that learns.Proceedings of The Sixth National Conference on Artificial Intelligence (pp. 494–498). Seattle, WA: Morgan Kaufmann.
Quinlan, J.R. (1986). Induction of decision trees.Machine Learning, 1 81–106.
Ruff, R.A., & Dietrich, T.G. (1989). What good are experiments?Proceedings of The Sixth International Workshop on Machine Learning (pp. 109–112). Ithaca, NY: Morgan Kaufmann.
Samuel, A.L. (1959). Some studies in machine learning using the game of checkers.IBM Journal, 3 211–229.
Scott, P.D., & Markovitch, S. (1989a). Learning novel domains through curiosity and conjecture.Proceedings of International Joint Conference for Artificial Intelligence (pp. 669–674). San Mateo, CA: Morgan Kaufmann.
Scott, P.D., & Markovitch, S. (1989b). Uncertainty based selection of learning experiences.Proceedings of The Sixth International Workshop on Machine Learning (pp. 368–371). Ithaca, NY: Morgan Kaufmann.
Scott, P.D., & Markovitch, S. (1991). Representation generation in an exploratory learning system. In D. Fisher & M. Pizzani (Eds.),Concept formation: Knowledge and experience in unsupervised learning. Morgan Kaufmann.
Shannon, C.E., & Weaver, W. (1949).The Mathematical Theory of Communication. University of Illinois Press.
Tambe, M., & Newell, A. (1988). Some chunks are expensive.Proceedings of The Fifth International Conference on Machine Learning (pp. 451–458). Ann Arbor, MI: Morgan Kaufmann.
Utgoff, P.E. (1989). Improved training via incremental learning.Proceedings of The Sixth International Workshop on Machine Learning (pp. 362–365). Ithaca, NY: Morgan Kaufmann.
Valiant, L.G. (1984). A theory of the learnable.Communications of the ACM, 27 1134–1142.
Wilkins, D.C., & Ma, Y. (1989). Sociopathic knowledge bases (Technical Report UIUCDCS-R-89-1538). Urbana-Champaign, IL: University of Illinois, Department of Computer Science.
Winston, P.H. (1975). Learning structural descriptions from examples. In P. Winston (Ed.),The psychology of computer vision. New York: McGraw-Hill.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Markovitch, S., Scott, P.D. Information filtering: Selection mechanisms in learning systems. Mach Learn 10, 113–151 (1993). https://doi.org/10.1007/BF00993503
Received:
Accepted:
Issue Date:
DOI: https://doi.org/10.1007/BF00993503