Abstract
Unsupervised competitive neural networks have been recognized as a powerful tool for pattern analysis, feature extraction and clustering analysis. The global competitive structures tend to critically depend on the number of elements in the networks and on the noise property of the space. In order to overcome these problems in this work is presented an unsupervised competitive neural network characterized by units with an adaptive threshold and local inhibitory interactions among its cells. Each neural unit is based on a modified competitive learning law in which the threshold changes in learning stage. It is shown that the proposed neuron is able, during the learning stage, to perform an automatic selection of patterns that belong to a cluster, moving towards its centroid. The properties of this network, are examined in a set of simulations adopting a data set composed of Gaussian mixtures.
This is a preview of subscription content, log in via an institution to check access.
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
KOHONEN, T.: “Self-organizing maps”, Springer-Verlag, Third Edition 2001.
MAO J., JAIN ANIL. K., “Artificial Neural Networks for Feature extraction and multivariate data Projection”, IEEE Trans. Neural Networks, vol. 6, pp. 296–317, Mach. 1995
McNEILL D., Card C. H., Murray A. F., “An Investigation of Competitive Learning for Autonomous Cluster Identification in Embedded Systems”, International Journal of Neural Systems, vol. 11, n. 4, (2001), pp. 389–398
BISHOP C. M., “Neural Networks for Pattern Recognition”, Oxford University Press (1995)
Xu L., “Best Harmony, Unified RPCL and Automated Model Selection for Unsupervised and Supervised Learning on Gaussian Mixtures, Three-Layer Nets and ME-RBF-SVM Models”, International Journal of Neural Systems, vol. 11, n. 1, (2001), pp. 43–69
Ito R. and Shida T. and Kindo T. “Competitive models for unsupervised clustering” Transactions of the Institute of Electronics Information and Communication Engineers D-II, Vol. J79D-II, Number 8, pp. 1390–400, 1996
J MEADOR, P. HYLANDER, “A Pulse Coded Winner-Take-All Circuit” Proc. Int. Conf. On Neural Networks Vol. II, 299–302, 1996
PEDRONI A. Volnei, “Inhibitory Mechanism Analysis of Complexity O(N) MOS Winner-Take-All Networks” IEEE Trans. On Circuits and Systems — 1 Fundamental Theory and Applications, Vol. 42, No. 3, pp., March 1995.
E. CHIARANTONI, G. FORNARELLI, S. VERGURA, “Redundancy Reduction in Environmental Data Set by means of Unsupervised Neural Network” International Joint Conference on Neural Networks-IJCNN, Honolulu, Hawaii, U.S.A. 12–17 May 2002
E. CHIARANTONI, G. FORNARELLI, F. VACCA, S. VERGURA “Dynamical Threshold for a feature detector Neural Model” INNS-IEEE International Joint Conference on Neural Networks Washington, DC, 14–19 July 2001
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2002 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Chiarantoni, E., Acciani, G., Fornarelli, G., Vergura, S. (2002). Robust Unsupervised Competitive Neural Network by Local Competitive Signals. In: Dorronsoro, J.R. (eds) Artificial Neural Networks — ICANN 2002. ICANN 2002. Lecture Notes in Computer Science, vol 2415. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-46084-5_156
Download citation
DOI: https://doi.org/10.1007/3-540-46084-5_156
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-44074-1
Online ISBN: 978-3-540-46084-8
eBook Packages: Springer Book Archive