Abstract
It is best to learn a large theory in small pieces. An approach called “layered learning” starts by learning an approximately correct theory. The errors of this approximation are then used to construct a second-order “correcting” theory, which will again be only approximately correct. The process is iterated until some desired level of overall theory accuracy is met. The main advantage of this approach is that the sizes of successive training sets (errors of the hypothesis from the last iteration) are kept low. General lower-bound PAC-learning results are used in this paper to show that optimal layered learning results in the total training set size (t) increasing linearly in the number of layers. Meanwhile the total training and test set size (m) increases exponentially and the error (e) decreases exponentially. As a consequence, a model of layered learning which requires that t, rather than m, be a polynomial function of the logarithm of the concept space would make learnable many concept classes which are not learnable in Valiant's PAC model.
This is a preview of subscription content, log in via an institution.
Preview
Unable to display preview. Download preview PDF.
References
M. Bain. Experiments in non-monotonie first-order induction. In Proceedings of the Eighth International Machine Learning Workshop, San Mateo, CA, 1991. Morgan-Kaufmann.
M. Bain and S. Muggleton. Non-monotonic learning. In D. Michie, editor, Machine Intelligence 12. Oxford University Press, 1991.
A. Ehrenfeucht, D. Haussler, M. Kearns, and L. Valiant. A general lower bound on the number of examples needed for learning. In COLT 88: Proceedings of the Conference on Learning Theory, pages 110–120, San Mateo, CA, 1988. Morgan-Kaufmann.
S. Muggleton. Inductive Logic Programming. New Generation Computing, 8(4):295–318, 1991.
J.R. Quinlan. Discovering rules from large collections of examples: a case study. In D. Michie, editor, Expert Systems in the Micro-electronic Age, pages 168–201. Edinburgh University Press, Edinburgh, 1979.
L. Valiant. A theory of the learnable. Communications of the ACM, 27(11):1134–1142, 1984.
S. Wrobel. On the proper definition of minimality in specialization and theory revision. In P.Brazdil, editor, EWSL-93, pages 65–82, Berlin, 1993. Springer-Verlag.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1993 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Muggleton, S. (1993). Optimal layered learning: A PAC approach to incremental sampling. In: Jantke, K.P., Kobayashi, S., Tomita, E., Yokomori, T. (eds) Algorithmic Learning Theory. ALT 1993. Lecture Notes in Computer Science, vol 744. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-57370-4_35
Download citation
DOI: https://doi.org/10.1007/3-540-57370-4_35
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-57370-8
Online ISBN: 978-3-540-48096-9
eBook Packages: Springer Book Archive