Abstract
Knowledge-Based Systems are based on an often defectuous knowledge, be this knowledge acquired from experts or learned from examples.
This paper presents a strategy designed to cope with defectuous knowledge: given a set of rules, it builds a similarity function over the work space of the problem. This similarity function together with a set of examples then enables case-based reasoning, through aK-nearest-neighbour-like process.
Compared to other case-based reasoning techniques, the advantage of this approach is the following: the “topology” of the space is automatically induced from the given rules, instead of being explicitly provided (and tuned) by the expert.
Similar content being viewed by others
References
S. Andreassen, M. Woldbye, B. Falk and S.K. Andersen, MUNIN: a causal probabilistic network for interpretation of electromiographic findings,Proc. 10th IJCAI (1987) pp. 366–372.
M. Ayel, Protocols for coherence checking in expert systems knowledge bases,Proc. ECAI-88. München (August 1988) pp. 220–225.
R. Bareiss,Exemplar-Based Knowledge Acquisition (Academic Press, Boston, MA, 1989).
G. Bisson, KBG, a knowledge based generalizer,7th Int. Conf. on Machine Learning, eds R. Porter and B. Mooney (Morgan Kaufmann, Austin, TX, 1990).
L. Breiman, J.H. Friedman, R.A. Olshen and C.J. Stone,Classification and Regression by Trees (Wadsworth, Belmont, CA, 1984).
P. Brito and E. Diday, Pyramidal representation of symbolic objects, in:Knowledge, Data and Computer-Assisted Decisions, eds. M. Schader and W. Gaul, NATO ASI Series, Vol. 61 (Springer, 1991) pp. 3–16.
B.G. Buchanan and E.H. Shortliffe,Rule-Base Expert Systems: The MYCIN Experiments of the Stanford Heuristic Programming Project (Addison Wesley, Reading, MA, 1984).
J.G. Carbonell, Derivational analogy: a theory of reconstructing problem solving and expertise acquisition, in:Machine Learning: An Artificial Intelligence Approach, II, eds. R.S. Michalski, J.G. Carbonnell and T.M. Mitchell (Springer, 1986) pp. 371–392.
B. Cestnik, I. Bratko and I. Kononenko, ASSISTANT 86: A knowledge elicitation tool for sophisticated users, in:Progress in Machine Learning, Proc. EWSL 1987, eds. 1. Bratko and N. Lavrac (Sigma Press, 1987).
P. Clark and T. Niblett, Induction in noisy domains, ibid.
C. Decaestecker, Incremental concept formation with attribute selection,Proc. EWSL 1989, ed K. Morik (Pitman, London, 1989) pp. 49–58.
E. Diday, Knowledge representation and symbolic data analysis, in:Decision and Expert Systems, eds. W. Gaul and M. Schader (Springer, 1990) pp. 17–34.
J. Doyle, A truth-maintenance system, Art. Int. 12 (1979) 231–272.
J. De Kleer, An assumption-based TMS, Al Journal 28 (1986) 127–162.
F. Esposito, D. Malerba and G. Semeraro, Classification of incomplete structural descriptions using a probabilistic distance measure, in:Symbolic-Numeric Data Analysis and Learning, eds E. Diday and Y. Lechevallier (Nova Science, 1990) pp. 469–482.
J.G. Ganascia, AGAPE et CHARADE, deux techniques d'apprentissage symbolique appliquées à la construction de bases de connaissances, Thèse d'Etat, Orsay (1987).
Ho Tu Bao, E. Diday and M. Summa, Generating rules for expert systems from observations,7th Conf. on Expert Systems and Applications, Avignon (1987).
B. Indurkhya, On the role of interpretive analogy in learning, in:Algorithmic Learning Theory. eds. S. Arikawa et al. (Springer, 1990) pp. 174–189.
D. Kibler and D.A. Aha, Learning representative exemplars of concepts: An initial case study.Proc. 4th IWML, reprinted in:Readings in Machine Learning, eds. J.W. Shavlik and T.G. Dietterich (Morgan Kaufmann, 1990) pp. 108–115.
Y. Kodratoff and E. Diday (eds.),Induction Symbolique-Numérique (Cepadues, 1991).
J.L. Kolodner,Retrieval and Organizational Strategies in Conceptual Memory: A Computer Model (Lawrence Erlbaum Associates, Hillsdale, NJ, 1984).
S. MacLane and G. Birkhoff,Algebra (Macmillan, New York, 1967).
R.S. Michalski, A theory and methodology for inductive learning, in:Machine Learning: An Artificial Intelligence Approach, I, eds. R.S. Michalski, J.G. Carbonnell and T.M. Mitchell (Springer. 1983) pp. 83–134.
R.S. Michalski, I. Mozetic, J. Hong and N. Lavrac, The AQ15 inductive learning system: an overview and experiment,Proc. IMAL, Orsay (1986).
N. Nilsson and M. Genesereth,Logical Foundations of Artificial Intelligence (Morgan Kaufmann, 1987).
R. Quinlan, Induction of decision trees, Machine Learning 1 (1986) 81–106.
S. Rajamoney and R. DeJong, The classification, detection and handling of imperfect theory problems,Proc. IJC AI (1987).
J.A. Robinson, A machine-oriented logic based on the resolution principle, J. ACM 12 (1965) 23–41.
M.C. Rousset, On the consistency of knowledge base using the Covadis system,Proc. Computational Intelligence (Canada) (1988) pp. 166–170.
S.L. Salzberg,Learning with Nested Generalized Exemplars (Kluwer Academic, 1990).
J. Schlimmer and Granger, Incremental learning from noisy data, Machine Learning 1 (1986) 317–354.
M. Sebag and M. Schoenauer, Incremental learning of rules and meta-rules,7th Int. Conf. on Machine Learning, eds. R. Porter and B. Mooney (Morgan Kaufmann, Austin, TX, 1990).
M. Sebag and M. Schoenauer, Learning to control inconsistent knowledge,10th Euro. Conf. on Artificial Intelligence, ed. B. Neumann, Vienna, Austria (1992) pp. 479–483.
P. Smets, E.H. Mamdani, D. Dubois and H. Prade,Non-Standard Logics for Automated Reasoning (Academic Press, London, 1988).
R. Stepp and R.S. Michalski, Conceptual clustering: inventing goal-oriented classifications of structure objects, in:Machine Learning: An Artificial Intelligence Approach, I, eds. R.S. Michalski, J.G. Carbonnell and T.M. Mitchell, Vol. 2 (Morgan Kaufmann, 1986) pp. 471–498.
M. Summa, Interpreting factorial axes, in:Knowledge, Data and Computer-Assisted Decisions, eds. M. Schader and W. Gaul, NATO ASI Series, Vol. 61 (Springer, 1991).
K. Sycara, Case-based learning with a mixed paradigm, in:Symbolic Numeric Data Analysis and Learning, eds. E. Diday and Y. Lechevallier (Nova Science Publishers, 1991) pp. 159–170.
M. Valtorta, More results on the complexity on knowledge-based refinements: belief networks,7th Int. Conf. on Machine Learning, eds. R. Porter and B. Mooney (Morgan Kaufmann, Austin, TX, 1990).
N. Zlatareva, Distributed verification: a new formal approach for verifying knowledge-based systems,Proc. 1st World Congress on Expert Systems, ed. J. Liebowitz (Pergamon Press, 1991) pp. 1021–1029.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Sebag, M., Schoenauer, M. A numerical strategy to defectuous knowledge using. Ann Oper Res 55, 379–401 (1995). https://doi.org/10.1007/BF02030868
Issue Date:
DOI: https://doi.org/10.1007/BF02030868