Abstract
This paper presents a learning algorithm which constructs an optimised piecewise linear classifier for n-class problems.
In the first step of the algorithm initial positions of the discriminating hyperplanes are determined by linear regression for each pair of classes. To optimise these positions depending on the misclassified patterns an error criterion function is defined. This function is minimised by a gradient descent procedure for each hyperplane separately. As an option in the case of non-convex classes, a clustering procedure decomposing the classes into appropriate subclasses can be applied. The classification of patterns is defined on a symbolic level on the basis of the signs of the discriminating hyperplanes.
This work was supported by the German Ministry of Research and Technology within the project WISCON
Chapter PDF
Similar content being viewed by others
References
Michie, D., Spiegelhalter, D., Taylor, C. (Eds.): Machine Learning, Neural and Statistical Classification. Results of the Esprit project STATLOG (to appear)
Meyer-Brötz, G., and Schürmann, J.: Methoden der automatischen Zeichenerkennung. Akademie-Verlag, Berlin (1970)
Unger, S., Wysotzki, F.: Lernfähige Klassifizierungssysteme. Akademie-Verlag, Berlin (1981)
Duda, R.O., Hart, P.E.: Pattern Classification and Scene Analysis. John Wiley (1973)
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1994 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Schulmeister, B., Wysotzki, F. (1994). The piecewise linear classifier DIPOL92. In: Bergadano, F., De Raedt, L. (eds) Machine Learning: ECML-94. ECML 1994. Lecture Notes in Computer Science, vol 784. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-57868-4_86
Download citation
DOI: https://doi.org/10.1007/3-540-57868-4_86
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-57868-0
Online ISBN: 978-3-540-48365-6
eBook Packages: Springer Book Archive