Abstract
In this paper, two important issues concerning pattern recognition by neural networks are studied: a new model of hebbian learning, as well as the effect of the network capacity when retrieving patterns and performing clustering tasks. Particularly, an explanation of the energy function when the capacity is exceeded: the limitation in pattern storage implies that similar patterns are going to be identified by the network, therefore forming different clusters.
This ability can be translated as an unsupervised learning of pattern clusters, with one major advantage over most clustering algorithms: the number of data classes is automatically learned, as confirmed by the experiments. Two methods to reinforce learning are proposed to improve the quality of the clustering, by enhancing the learning of patterns relationships.
As a related issue, a study on the net capacity, depending on the number of neurons and possible outputs, is presented, and some interesting conclusions are commented.
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.
References
Erdem, M.H., Ozturk, Y.: A New family of Multivalued Networks. Neural Networks 9,6, 979–989 (1996)
Hebb, D.O.: The Organization of Behavior. Wiley, New York (1949)
Hertz, J., Krogh, A., Palmer, R.G.: Introduction to the theory of neural computation. Lecture Notes, vol. 1. Addison-Wesley, Reading (1991)
Hopfield, J.J.: Neural networks and physical systems with emergent collective computational abilities. In: Proc. of National Academy of Sciences USA, vol. 79, pp. 2254–2558 (1982)
Hopfield, J.J.: Neurons with graded response have collective computational properties like those of two-state neurons. In: Proceedings of the National Academy of Sciences USA, vol. 81, pp. 3088–3092 (1984)
López-Rodríguez, D., Mérida-Casermeiro, E.: Matrix Bandwidth Minimization: A Neural Approach. ICCMSE 1, 324–327 (2004)
Mérida Casermeiro, E.: Red Neuronal recurrente multivaluada para el reconocimiento de patrones y la optimización combinatoria, Ph. D. dissertation (in spanish). Univ. Málaga, España (2000)
Mérida Casermeiro, E., Muñoz-Pérez, J.: MREM: An associative autonomous recurrent network. Journal of Intelligent and Fuzzy Systems 12(3-4), 163–173 (2002)
Mérida Casermeiro, E., Muñoz Pérez, J., Benítez Rochel, R.: A recurrent multivalued neural network for the N-queens problem. In: Mira, J., Prieto, A.G. (eds.) IWANN 2001. LNCS, vol. 2084, pp. 522–529. Springer, Heidelberg (2001)
Mérida Casermeiro, E., Muñoz-Pérez, J., García-Bernal, M.A.: An Associative Multivalued Recurrent Network. In: Garijo, F.J., Riquelme, J.-C., Toro, M. (eds.) IBERAMIA 2002. LNCS (LNAI), vol. 2527, pp. 509–518. Springer, Heidelberg (2002)
Mérida-Casermeiro, E., López-Rodríguez, D.: Multivalued Neural Network for Graph MaxCut Problem. ICCMSE 1, 375–378 (2004)
Ozturk, Y., Abut, H.: System of associative relationships (SOAR). In: Proceedings of ASILOMAR (1997)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2006 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Mérida-Casermeiro, E., López-Rodríguez, D. (2006). Hebbian Iterative Method for Unsupervised Clustering with Automatic Detection of the Number of Clusters with Discrete Recurrent Networks. In: Marín, R., Onaindía, E., Bugarín, A., Santos, J. (eds) Current Topics in Artificial Intelligence. CAEPIA 2005. Lecture Notes in Computer Science(), vol 4177. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11881216_26
Download citation
DOI: https://doi.org/10.1007/11881216_26
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-45914-9
Online ISBN: 978-3-540-45915-6
eBook Packages: Computer ScienceComputer Science (R0)