Abstract
Learning algorithms from the fields of artificial neural networks and machine learning, typically, do not take any costs into account or allow only costs depending on the classes of the examples that are used for learning. As an extension of class dependent costs, we consider costs that are example, i.e. feature and class dependent. We derive a cost-sensitive perceptron learning rule for non-separable classes, that can be extended to multi-modal classes (DIPOL) and present a natural cost-sensitive extension of the support vector machine (SVM).
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Clarke, F.H.: Optimization and Nonsmooth Analysis. Canadian Math. Soc. Series of Monographs and Advanced Texts. John Wiley & Sons, Chichester (1983)
Cristianini, N., Shawe-Taylor, J.: An Introduction to Support Vector Machines (and Other Kernel-Based Learning Methods). Cambridge University Press, Cambridge (2000)
Duda, R.O., Hart, P.E.: Pattern Classification and Scene Analysis. John Wiley & Sons, New York (1973)
Elkan, C.: The foundations of Cost-Sensitive learning. In: Nebel, B. (ed.) Proceedings of the seventeenth International Conference on Artificial Intelligence (IJCAI 2001), August 4-10, pp. 973–978. Morgan Kaufmann Publishers, Inc., San Francisco (2001)
Geibel, P., Wysotzki, F.: Using costs varying from object to object to construct linear and piecewise linear classifiers. Technical Report 2002-5, TU Berlin, Fak. IV (2002), http://ki.cs.tu-berlin.de/~geibel/publications.html
Kukar, M., Kononenko, I.: Cost-sensitive learning with neural networks. In: Prade, H. (ed.) Proceedings of the 13th European Conference on Artificial Intelligence (ECAI 1998), pp. 445–449. John Wiley & Sons, Chichester (1998)
Lenarcik, A., Piasta, Z.: Rough classifiers sensitive to costs varying from object to object. In: Polkowski, L., Skowron, A. (eds.) RSCTC 1998. LNCS (LNAI), vol. 1424, pp. 222–230. Springer, Heidelberg (1998)
Lin, Y., Lee, Y., Wahba, G.: Support vector machines for classification in nonstandard situations. Machine Learning 46(1-3), 191–202 (2002)
Margineantu, D.D., Dietterich, T.G.: Bootstrap methods for the costsensitive evaluation of classifiers. In: Proc. 17th International Conf. on Machine Learning, pp. 583–590. Morgan Kaufmann, San Francisco (2000)
Michie, D., Spiegelhalter, D.H., Taylor, C.C.: Machine Learning, Neural and Statistical Classification. Series in Artificial Intelligence. Ellis Horwood (1994)
Nedic, A., Bertsekas, D.P.: Incremental subgradient methods for nondifferentiable optimization. SIAM Journal on Optimization, 109–138 (2001)
Schulmeister, B., Wysotzki, F.: Dipol - a hybrid piecewise linear classifier. In: Nakeiazadeh, R., Taylor, C.C. (eds.) Machine Learning and Statistics: The Interface, pp. 133–151. Wiley, Chichester (1997)
Unger, S., Wysotzki, F.: Lernfähige Klassifizierungssysteme (Classifier Systems that are able to Learn). Akademie-Verlag, Berlin (1981)
Vapnik, V.N.: The Nature of Statistical Learning Theory. Springer, New York (1995)
Wysotzki, F., Müller, W., Schulmeister, B.: Automatic construction of decision trees and neural nets for classification using statistical considerations. In: DellaRiccia, G., Lenz, H.-J., Kruse, R. (eds.) WADS 1989. CISM Courses and Lectures, vol. 382. Springer, Heidelberg (1997)
Yang, J., Parekh, R., Honavar, V.: Comparison of performance of variants of single-layer perceptron algorithms on non-separable data. Neural, Parallel and Scientific Computation 8, 415–438 (2000)
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
Geibel, P., Brefeld, U., Wysotzki, F. (2003). Learning Linear Classifiers Sensitive to Example Dependent and Noisy Costs. In: R. Berthold, M., Lenz, HJ., Bradley, E., Kruse, R., Borgelt, C. (eds) Advances in Intelligent Data Analysis V. IDA 2003. Lecture Notes in Computer Science, vol 2810. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-45231-7_16
Download citation
DOI: https://doi.org/10.1007/978-3-540-45231-7_16
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-40813-0
Online ISBN: 978-3-540-45231-7
eBook Packages: Springer Book Archive