Abstract
This paper proposes a novel operator, based on the negation, for specializing the hypotheses inductively generated by any system that learns structural descriptions from positive and negative examples or, equivalently, learns intensional definitions of logical relations. Such a specializing operator adds the negation of one or more literals of a misclassified example to the Horn clause representation of an inconsistent hypothesis, after having properly turned constants into variables. The search for the literals to be added is firstly performed in a set named reduced base of consistent specializations and, in case of failure, it is extended to the augmented base of consistent specializations. Indeed, two theorems prove that clauses generated by adding literals in the former set preserve the consistency property and are most general specializations of the inconsistent hypothesis. On the contrary, the consistency property of clauses generated by adding literals in the latter set has to be checked on the misclassified example. The search strategy takes advantage of the structure of the set of the linked Horn clauses,
, ordered by the generality relation (≤). Some clarifying examples and experimental results are also presented.
Keywords
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
This is a preview of subscription content, log in via an institution.
Preview
Unable to display preview. Download preview PDF.
References
P.E. Utgoff: Incremental Induction of Decision Trees. Machine Learning 4, 161–186 (1989)
J. Hong, I. Mozetic, R.S. Michalski: AQ15: Incremental Learning of Attribute-Based Descriptions from Examples, the Method and User's Guide. Department of Computer Science, University of Illinois at Urbana-Champaign, Urbana, Illinois, UIUCDCS-F-86-949 (1986)
D.H. Fisher: Knowledge Acquisition Via Incremental Conceptual Clustering. Ph.D.dissertation, University of California, Irvine (1987)
M. Lebowitz: Experiments with Incremental Concept Formation: UNIMEM. Machine Learning 2, 103–138 (1987)
T.M. Mitchell: Generalization as Search. Artificial Intelligence 18, 203–226 (1982)
P.H. Winston: Learning Structural Descriptions from Examples. In: P.H. Winston (ed.): The psychology of computer vision. New York: McGraw Hill 1975
S.A. Vere: Induction of concepts in the predicate calculus. In: Proceedings of the 4th IJCAI. Tbilisi, USSR: Morgan Kaufmann 1975, pp. 281–287
F. Hayes-Roth: Schematic classification problems and their solution. Pattern Recognition, 105–113 (1974)
B.G. Buchanan and T.M. Mitchell: Model-directed learning of production rules. In: D.A. Waterman and F. Hayes-Roth (eds.): Pattern-Directed Inference Systems. New York: Academic Press 1978
J.A. Bentrup, G.J. Mehler, J.D. Riedsel: INDUCE 4: A Program for Incrementally Learning Structural Descriptions from Examples. Department of Computer Science, University of Illinois at Urbana-Champaign, Urbana, Illinois, UIUCDCS-F-87-958 (1987)
R.S. Michalski: Pattern Recognition as Rule-Guided Inductive Inference. IEEE Transactions on Pattern Analysis and Machine Intelligence PAMI-2, 4, 349–361 (1980)
F. Esposito: Automated acquisition of production rules by empirical supervised learning methods. In: M. Schader (ed.): Data, Expert Knowledge and Decisions, (Vol. II). Heidelberg: Springer-Verlag 1990
G. Semeraro: Un Sistema per l'Apprendimento Induttivo Concettuale da Esempi con Logica Variable-Valued.Laurea dissertation (also available as LACAM Technical Report, Dipartimento di Informatica, Università di Bari) (1988)
K.L. Clark: Negation as failure. In: H. Gallaire and J. Minker (eds.): Logic and Databases. New York: Plenum Press 1978
N. Helft: Inductive Generalization: A Logical Framework. In: I. Bratko, N. Lavrac (eds.): Progress in Machine Learning — Proceedings of EWSL 87. Wilmslow: Sigma Press 1987
G.D. Plotkin: A Note on Inductive Generalization. In: B. Meltzer and D. Michie (eds.): Machine Intelligence 5. Edinburgh: University Press 1970, pp. 153–163
K. VanLehn: Efficient Specialization of Relational Concepts. Machine Learning 4, 99–106 (1989)
F. Esposito, G. Semeraro and D. Malerba: Inductive Specialization: An Analytic Approach. LACAM Technical Report, Dipartimento di Informatica, Università di Bari (1992)
R.S. Michalski: A Theory and Methodology of Inductive Learning. Artificial Intelligence 20, 111–161 (1983)
F. Esposito, D. Malerba, G. Semeraro, E. Annese, G. Scafuro: Empirical Learning Methods for Digitized Document Recognition: An Integrated Approach to Inductive Generalization. In: Proceedings of the 6th Conference on Artificial Intelligence Applications. Santa Barbara, CA: IEEE Comp. Soc. Press 1990, pp. 37–45
F. Esposito, D. Malerba and G. Semeraro: Flexible Matching for Noisy Structural Descriptions. In: Proceedings of the 12th IJCAI. Sydney, Australia: Morgan Kaufmann 1991, pp. 658–664
F. Esposito, G. Semeraro and D. Malerba: A Syntactic Distance for Partially Matching Learned Concepts Against Noisy Structural Object Descriptions. International Journal of Expert Systems 4, 409–451 (1992)
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1993 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Esposito, F., Malerba, D., Semeraro, G. (1993). Negation as a specializing operator. In: Torasso, P. (eds) Advances in Artificial Intelligence. AI*IA 1993. Lecture Notes in Computer Science, vol 728. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-57292-9_55
Download citation
DOI: https://doi.org/10.1007/3-540-57292-9_55
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-57292-3
Online ISBN: 978-3-540-48038-9
eBook Packages: Springer Book Archive