Abstract
In a competitive neural network, a process unit (node) in the competitive layer is completely described by the vector of weight from the input node to it. Each such weight vector becomes the centroid of a cluster of inputs since the principal function of a competitive learning network is discovers cluster of overlapping input. In this paper we propose a competitive neural network where each process unit has a couple of weight vectors (dipoles) that becomes a line segment as representation of a cluster. A weight update is formulated such that the dipole associated with each process unit is as near as possible to all the input samples for which the node is the winner of the competition. This network allows the formation of groups or categories by means of unsupervised learning, where each class or category is identified by a line segment instead of a centroid. The line segment leads to a better representation of a group or class that a centroid that gives us only the position of the cluster. The network has been applied to the formation of groups or categories using the data IRIS, where the unsupervised learning algorithms reach between 12 and 17 incorrect classifications. However, while many partitional clustering algorithms and competitive neural networks are only suitable for detecting hyperspherical-shaped clusters, the proposed network gets only 5 incorrect classifications and is also suitable for detecting hyperspherical-shaped 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.
Similar content being viewed by others
References
Grossberg, S. Neural expectation: Cerebellar and retinal analogues of cells fired by unlearnable and learnable pattern classes, Kybernetik, 10: 49–57, 1972.
Grossberg, S. Adaptative pattern classification and universal recording: I. Parallel development and coding of neural detectors, Biolog. Cybernetics, 23: 121–134, 1976.
von der Malsburg, C. Self-organization of orientation sensitive cells in the striate cortex, Kybernetik, 14: 85–100, 1973.
Amari, S. and Takeuchi, M. Mathematical theory on formation of category detecting nerve cells, Biological Cybernetics, 29: 127–136, 1978.
Amari, S-I. Field theory of self-organizing neural nets, IEEE Transactions on Systems, Man and Cybernetics, SMC-13: 741–748, 1983.
Bienstock E., Cooper, E. & Munro, P. Theory for the development of neural selectivity: Orientation specificy and binocular interaction in visual cortex, Journal of Neuroscience, 2: 32–48, 1982.
Rumelhart, D. and Zipser, D. Feature discovery by competitive learning, Cognitive Science, 9: 75–112, 1985.
Ahalt, S.C., Krishnamurphy, A.K., Chen P. and Melton D.E. Competitive Learning Algorithms for Vector Quantization, Neural Networks, 3: 277–290, 1990.
Yair, E.K., Zeger K. and Gersho A. Competitive Learning and Soft Competition for Vector Quantizer Design, IEEE Trans. Signal Processing, 40 (2): 294–308, 1992.
Pal, N.R., Bezdek J.C.and Tsao E.C. Generalized Clustering Networks and Kohonen’s Self-Organizing Scheme, IEEE Trans. Neural Networks, 4 (4): 549–557, 1993.
Xu, L., Krzyzak A. and Oja E. “Rival Penalized Competitive Learning for Clustering Analysis, RBF Net, and Curve Detection,” IEEE Trans. Neural Networks, 4 (4): 636–649, 1993.
Ueda, N. and Nakano R. A New Competitive Learning Approach Based on an Equidistortion Principle for Designing Optimal Vector Quantizers, Neural Networks, 7 (8): 1211–1227, 1994.
Uchiyama, T. and Arbib M.A. Colour image segmentation using competitive learning, IEEE Trans. on Pattern Analysis and Machine Intelligence, 16 (12): 1197–1206, 1994.
Mao, J. and Jain A.K. A Self-Organizing Network for Hyperellipsoidal Clustering (HEC), IEEE Trans. Neural Networks, 7(1): 16–29, 1996.
Hwang, W.J., Ye B.Y. and Liao S.C. A novel entropy-constrained competitive learning algorithm for vector quantization. Neurocomputing, 25: 133–146, 1999.
Zhang, Y.J. and Liu Z.Q. Seft-splitting competitive learning: A New on-line clustering paradigm. IEEE Trans. Neural Networks, 13(2): 369–380, 2002.
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
García-Bernal, M., Muñoz-Pérez, J., Gómez-Ruiz, J., Ladrón de Guevara-López, I. (2003). A Competitive Neural Network based on dipoles. In: Mira, J., Álvarez, J.R. (eds) Computational Methods in Neural Modeling. IWANN 2003. Lecture Notes in Computer Science, vol 2686. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-44868-3_51
Download citation
DOI: https://doi.org/10.1007/3-540-44868-3_51
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-40210-7
Online ISBN: 978-3-540-44868-6
eBook Packages: Springer Book Archive