Abstract
Classification based on the Bayes criterion minimizes the probability of classification error. In order to apply this criterion, one has to know the probability densities of each class of data. Based on the Parzen density estimation, a new method is derived. The number of operations involved in the Parzen estimation is reduced by using the vector quantization property of Self Organizing Feature Mapping (SOFM). The width of the kernels is made dependent on the variance of the samples in the clusters.
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
B.W. Silverman, Density Estimation for Statistics and Data Analysis, Chapman and Hall, 1986.
L.P.J. Veelenturf, Analysis and Applications of Artificial Neural Networks, Prentice Hall, 1995.
P.M. Murphy and D.W. Aha. Uci repository of machine learning databases. Irvine, University of California, Department of Information and Computer Science (anonymous ftp to ics.uci.eduinpub/machine-learning database).
J.L. Voz, M. Verleysen, P. Thissen, and J.D. Legat. Suboptimal Bayesian classification by vector quantization with small clusters. In Proceedings ESANN, pages 153–160, Brussel 1995.
K. Fukunaga, Introduction to Statistical Pattern Recognition, 2nd edition, Academic Press, 1990.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1995 Springer-Verlag London Limited
About this paper
Cite this paper
Lokerse, S.H., Veelenturf, L.P.J., Beltman, J.G. (1995). Density Estimation Using SOFM and Adaptive Kernels. In: Kappen, B., Gielen, S. (eds) Neural Networks: Artificial Intelligence and Industrial Applications. Springer, London. https://doi.org/10.1007/978-1-4471-3087-1_39
Download citation
DOI: https://doi.org/10.1007/978-1-4471-3087-1_39
Publisher Name: Springer, London
Print ISBN: 978-3-540-19992-2
Online ISBN: 978-1-4471-3087-1
eBook Packages: Springer Book Archive