Abstract
This article examines the methods how to avoid an overfitting-effect within GeLog-systems. This effect can be observed in nearly all systems of inductive concept learning, if due to false classification of examples false, especially too specific theories, are learned. There are a number or procedures, how to counter the effects of the overfitting-effect or to avoid it. This article develops criteria for the selection of those procedures. In this context, the integrability into the GeLog-system, a system of genetic inductive logic programming, is of great importance. Finally, a filter procedure, based on the correlation heuristic, which is also used for top-down-pruning, is selected, as it promised the possible application to a relatively huge amount of problems. After that, the efficiency of the methods will be proven with the help of systematic experiments.
This scientific work was supported Habilitation Fellowship of the Bavarian Government 1999 and the German Academic Exchange Service (DAAD).
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Aha, D.W.: Incremental constructive induction: An instance-based approach. In: Proceedings of the 8th International Workshop on Machine Learning, Evanston, ILL, pp. 117–121. Morgan Kaufmann, San Francisco (1991)
Breimann, L., Friedmann, J., Olshen, R., Stone, C.: Classification and Regression Trees. Wadsworth & Brooks, Pacific Grove (1984)
Brunk, C., Pazzani, M.: An investigation of noise-tolerant relational concept learning algorithms. In: Proceedings of the 8th International Workshop on Machine Learning (1991)
Chaffer, C.: Overfitting avoidance as bias. In: Machine Learning: Proceedings of the Ninth International Conference, San Francisco, pp. 153–178. Morgan Kaufmann, San Francisco (1992)
Fürnkranz, J.: Efficient Pruning Methods for Relational Learning. PhD thesis, Technical University of Vienna (1994)
John, G., Kohavi, R., Pfleger, R.: Irrelevant features and the subset selection problem. In: Machine Learning: Proceedings of the 11th International Conference, pp. 121–129. Morgan Kaufmann Publishers, San Francisco (1994)
Kókai, G.: GeLog—A System Combining Genetic Algorithm with Inductive Logic Programming. In: Reusch, B. (ed.) Fuzzy Days 2001. LNCS, vol. 2206, pp. 326–345. Springer, Heidelberg (2001)
Matheus, C.J.: Adding domain knowledge to sbl through feature construction. In: Proceedings of the 8th National Conference on Artificial Intelligence, Boston, MA, pp. 803–808. AAAI Press, Menlo Park (1990)
Mingers, J.: An empirical comparison of pruning methods for decision tree induction. Machine Learning 4(2), 227–243 (1989)
Mitchell, T.: Learning sets of rules. Machine Learning 10, 274–305 (1997)
Niblett, T., Bratko, I.: Learning decision rules in noisy domains. In: Bramer, M. (ed.) Research and Development in Expert Systems III, Cambridge, pp. 24–25. Cambridge University Press, Cambridge (1986)
Pagallo, G., Haussler, D.: Boolean feature discovery in empirical learning. Machine Learning 5(1), 71–99 (1990)
Quinlan, J.: Simplifying decision trees. International Journal of Man-Machine Studies 27(3), 221–234 (1987)
Wolpert, D.H.: On overfitting avoidance as bias. Technical report, Technical Report SFI TR 92-03-5001Th e Santa Fe Institute, Santa Fe (1982)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2003 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Kókai, G. (2003). Development of Methods How to Avoid the Overfitting-Effect within the GeLog-System. In: Palade, V., Howlett, R.J., Jain, L. (eds) Knowledge-Based Intelligent Information and Engineering Systems. KES 2003. Lecture Notes in Computer Science(), vol 2774. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-45226-3_131
Download citation
DOI: https://doi.org/10.1007/978-3-540-45226-3_131
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-40804-8
Online ISBN: 978-3-540-45226-3
eBook Packages: Springer Book Archive