Abstract
In this paper, we compare several forms of deductive generalization from positive and negative examples. We show that there exist cases where the logical conditions under which such paradigms can take place just appear too restrictive and somewhat counter-intuitive. Moreover, some of these conditions, which can be checked in an efficient way, also prove useful when satisfied since they sometimes allow one to prune the space of potential generalizations. Departing from a standard logical framework, we then show how an intuitionistic account of deductive generalization relaxes those conditions to make them more natural.
Preview
Unable to display preview. Download preview PDF.
References
N.D. Belnap: How A Computer Should Think. In: G. Ryle (ed.): Contempory Aspects of Philosophy. Oriel Press (1977)
Ph. Besnard, E. Grégoire: Deductive Generalization in a Default Logic Setting. In: Proc. of the Second Int. Workshop on Nonmonotonic and Inductive Logics (NIL91). Lecture Notes in Computer Science. Berlin: Springer (1992)
M. Dummett: Elements of Intuitionism. Oxford University Press (1977)
Y. Kodratoff: Introduction to Machine Learning. London: Pitman (1988)
R. Michalski: A Theory and Methodology of Inductive Learning. In: Machine Learning: an A.I. Approach. Tioga (1983)
T. Mitchell: Version Spaces: an Approach to Concept Learning. Stanford University: Ph.D. Thesis (1978)
J. Nicolas: ALLY: un système logique pour la généralisation en apprentissage automatique. Université de Rennes I: Thèse d'Université (1987)
J. Nicolas: Consistency and Preference Criteria for Generalization Languages Handling Negation and Disjunction. In: Proc. ECAI-88. London: Pitman pp. 402–407 (1988)
R. Reiter: A Logic for Default Reasoning. Artificial Intelligence, 13, pp. 81–132 (1980)
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1992 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Besnard, P., Grégoire, E. (1992). About deductive generalization. In: Pearce, D., Wagner, G. (eds) Logics in AI. JELIA 1992. Lecture Notes in Computer Science, vol 633. Springer, Berlin, Heidelberg. https://doi.org/10.1007/BFb0023430
Download citation
DOI: https://doi.org/10.1007/BFb0023430
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-55887-3
Online ISBN: 978-3-540-47304-6
eBook Packages: Springer Book Archive