Abstract
We introduce a batch learning algorithm to design the set of prototypes of 1 nearest-neighbour classifiers. Like Kohonen's LVQ algorithms, this procedure tends to perform vector quantization over a probability density function that has zero points at Bayes borders. Although it differs significantly from their online counterparts since: (1) its statistical goal is clearer and better defined; and (2) it converges superlinearly due to its use of the very fast Newton's optimization method. Experiments results using artificial data confirm faster training time and better classification performance than Kohonen's LVQ algorithms.
Similar content being viewed by others
References
Bottou, L.: Online learning and stochastic approximation, In: David Saal (ed.), Online Learning and Neural Networks, Cambridge University Press, Cambridge, UK, 1998.
Cover, T. M. and Hart, P. E.: Nearest neighbor pattern classification, IEEE Trans. Inf. Th., IT-13 (1967), 21–27.
Gersho, A. and Gray, R. M.: Vector Quantization and Signal Compression, Kluwer Academic Publishers, Boston, MA, 1992.
Hestenes, M.: Conjugate Direction Methods in Optimization, Springer-Verlag, Berlin, New York, 1980.
Kohonen, T., Hynninen, J., Kangas, J., Laaksonen, J. and Torkkola, K.: Kari. LVQ_PAK. The learning vector quantization program package. Version 3.1, Laboratory of Computer and Information Science, Helsinki University of Technology, April 7, 1995.
Kohonen, T.: Self-Organizing Maps, 2nd edn, Springer-Verlag, Berlin, New York, 1996.
Lavigna, A.: Nonparametric classification using learning vector 1990.
Vapnik, V.: Estimation of Dependencies based on Empirical Data, Springer Series in Statistics, Springer-Verlag, Berlin, New York, 1982.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Bermejo, S., Cabestany, J. A Batch Learning Vector Quantization Algorithm for Nearest Neighbour Classification. Neural Processing Letters 11, 173–184 (2000). https://doi.org/10.1023/A:1009634824627
Issue Date:
DOI: https://doi.org/10.1023/A:1009634824627