Abstract
In this paper, we present a new paradigm for inductive learning, called second-order inductive learning. It differs from concept learning from examples in that examples are not instances of the hypothesis to be learned, but rather instances of a prototype (i.e., a typical member of the extension) of the hypothesis to be learned. The paradigm is introduced by means of an example problem from the field of conceptual modeling. We analyse the reasons why a naive solution to that problem is not fully satisfactory by studying the Version Space model. Once it is clear why this model is not directly applicable, we attempt to restore it by defining the notion of a Generalised Version Space model.
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
D. ANGLUIN & C.H. SMITH, 1983 ‘Inductive inference: theory and methods', Computing Surveys 15:3, 238–269.
P.A. FLACH, ‘Inductive methods in data modeling', unpublished.
P.A. FLACH, ‘On the significance of examples in inductive learning', submitted.
E.M. GOLD, 1967 ‘Language identification in the limit', Information and Control 10, 447–474.
P.D. LAIRD, 1988 Learning from good and bad data, Kluwer, Boston.
T.M. MITCHELL, 1982 ‘Generalization as search', Artificial Intelligence 18, 203–226.
D. VERMEIR & G.M. NIJSSEN, 1982 ‘A procedure to define the object type structure of a conceptual schema', Information Systems 7:4, 329–336.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1989 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Flach, P.A. (1989). Second-order inductive learning. In: Jantke, K.P. (eds) Analogical and Inductive Inference. AII 1989. Lecture Notes in Computer Science, vol 397. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-51734-0_62
Download citation
DOI: https://doi.org/10.1007/3-540-51734-0_62
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-51734-4
Online ISBN: 978-3-540-46798-4
eBook Packages: Springer Book Archive