Abstract
We consider the average error rate of classification as a function of the number of training examples. We investigate the upper and lower bounds of this error in the class of commonly used algorithms based on inductive learning from examples. As a result we arrive at the astonishing conclusion, that, contrary to what one could expect, the error rate of some algorithms does not decrease monotonically with number of training examples; it rather, initially increases up to a certain point and then it starts to decrease. Furthermore, the classification quality of some algorithms is as poor as that of a naive algorithm. We show that for simple monomials, even if we take an exponentially large training data set, the classification quality of some methods will not be better than if we took just one or several training examples.
Preview
Unable to display preview. Download preview PDF.
References
Anthony, M., Biggs, N.: Computational Learning Theory, Cambridge: Cambridge University Press (1992).
Bazan, J.: A Comparison of Dynamic and non-Dynamic Rough set Methods for Extracting Laws from Decision Table, Polkowski L., Skowron A. (eds.): Rough Sets in Knowledge Discovery. Heidelberg: Physica-Verlag (1998) 321–365.
Dietterich, T.: Machine Learning Research: Four Current Directions. Department of Computer Science, Oregon State University, Corvallis (1997).
Ejdys, P., Góra, G.:On Inductive Learning from Examples. Fundamenta Inforaticae (submited).
Grzymała-Busse, J. W.: Classification of Unseen Examples under Uncertainty. Fundamenta Informaticae, 30 (1997) 255–267. Press.
Grzymała-Busse, J. W.: A new version of the rule induction system LERS. Fundamenta Informaticae, 31 (1997) 27–39.
Grzymała-Busse, J. W.: LERS—a system for learning from examples based on rough sets. In: R. Słowiński, (ed.) Intelligent Decision Support, Dordrecht: Kluwer (1992) 3–18.
Hand, D. J.: Construction and Assesment of Classification rules. Chichester: John Wiley and Sons (1998).
Leja, F.: Differential and integeral calculus, Warsaw: PWN (1978). (In Polish)
Michalski, R., Carbonell, J. G. Mitchel, T. M. (ed): Machine Learning vol. I. Los Altos: Tioga/Morgan Kaufmann (1983).
Michalski, R. S., Mozetic, I., Hong, J., Lavrac, N.: The Multi-Purpose Incremental Learning System AQ15 and its Testing to Three Medical Domains, Proceedings of AAAI-86. San Mateo: Morgan Kaufmann (1986) 1041–1045.
Michalski, R., Wnęk, J.: Constructive Induction: An Automated Improvement of Knowledge Representation Spaces for Machine Learning, in Proceedings of a Workshop on Intelligent Information Systems, Practical Aspect of AI II, Augustów (1993) 188–236.
Michalski, R.: A Tutorial on Machine learning, data mining and knowledge discovery Principles and Applications, Zakopane (1997).
Mitchell, T. M.: Machine Learning, Portland: McGraw-Hill (1997).
Pawlak, Z.: Rough sets: Theoretical aspects of reasoning about data, Dordrecht: Kluwer (1991).
Skowron, A., Rauszer, C.: The Discernibility Matrices and Functions in Information Systems. R. Słowiński (ed.), Intelligent Decision Support. Handbook of Applications and Advances of the Rough Set Theory. Dordrecht: Kluwer (1992) 331–362.
Tsumoto, S., Tanaka H.: Incremental learning of probabilistic rules from clinical databases. Proceedings Information Processing and Management of Uncertainty on Knowledge Based Systems (IPMU-96), July 1–5, Granada, Spain, Universidad de Granada, vol. II, (1996) 1457–1462
Wegener, I.: The Complexity of Boolean Functions. Stuttgart: John Wiley and Sons (1987).
Ziarko, W., Shan, N.: Database Mining Using Rough Sets, Intelligent Information Systems IV Proceedings of the Workshop held in Augustów. Warsaw, IPIPAN (1995) 74–68.
Ziarko, W., Shan, N.: An incremental learning algorithm for constructing decision rules, Proceedings of the International Workshop on Rough Sets and Knowledge Discovery. Banff (1993) 335–346.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1999 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Ejdys, P., Góra, G. (1999). The more we learn the less we know? On inductive learning from examples. In: Raś, Z.W., Skowron, A. (eds) Foundations of Intelligent Systems. ISMIS 1999. Lecture Notes in Computer Science, vol 1609. Springer, Berlin, Heidelberg . https://doi.org/10.1007/BFb0095112
Download citation
DOI: https://doi.org/10.1007/BFb0095112
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-65965-5
Online ISBN: 978-3-540-48828-6
eBook Packages: Springer Book Archive