Abstract
This paper shows that the multivalued recurrent neural model (MREM) can be used as an autoassociative memory (multivalued counterpart of Hopfield network). The architecture of the proposed family of networks is inspired from bipolar Hopfield’s neural network (BH). We have modified the function of energy of the bipolar Hopfield model by a new function of the outputs of neurons that we are naming function of similarity as it measures the similarity between the outputs of neurons. When binary neurons are considered and the function product is used as a function of similarity, then the proposed model is identical to that of Hopfield. We have studied a method to load a set of patterns into the network. That method corresponds to the Hopfield’s one when bipolar neurons are been considered. Finally we show that an augmented network avoids the storage of undesirable patterns into the network, as the well-known effect of loading the opposite pattern into the Hopfield’s network. For this new storage technics an expression that allows to set bounds to the capacity of the network is obtained.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Mahmut H. Erdem & Y. Ozturk, A New family of Multivalued Networks, Neural Networks 9,6, pp. 979–989,1996.
J.J. Hopfield, Neural networks and physical systems with emergent collective computational abilities, Proc. of National Academy of Sciences USA,79, 2254–2558,1982.
J.J. Hopfield, Neurons with graded response have collective computational properties like those of two-state neurons, Proceedings of the National Academy of Sciences USA,81, 3088–3092, 1984.
Stanislaw Jankowski, Andrzej Lozowski and Jacek M. Zurada. Complex-Valued Multistate Neural Associative Memory. IEEE Transactions on Neural Networks 7 no 7 1491–1496, Nov. 1996.
L. Gislén, C. Peterson and B. Söderberg. Complex Schedulling with Potts Neural Networks. Neural Computation. 9, 805–831 (1992).
John Hertz, Anders Krogh and Richard G. Palmer Introduction to the theory of neural computation. Lecture Notes Volume I. Addison Wesley, 1991.
Kohring, G.A., On the Q-state Neuron Problem in Attractor Neural Networks. Neural Networks, Vol 6, 573–581, 1993.
E. Mérida Casermeiro, Red Neuronal recurrente multivaluada para el reconocimiento de patrones y la optimización combinatoria, Ph.D. dissertation. Univ. Málaga, Spain, (in spanish), 2000.
E. Mérida Casermeiro, G. Galán Marín, J. Muñoz Pérez. An Efficient Multivalued Hopfield Network for the Traveling Salesman Problem. Neural Processing Letters 14, 203–216, Dec. 2001.
E. Mérida Casermeiro, J. Muñoz Pérez, R. Benítez Rochel. A recurrent multivalued neural network for the N-queens problem. Lecture Notes in Computer Science 2084, 522–529, 2001.
A.J. Noest. Discrete-state phasor neural nets. Physical Review A38 2196–99, 1988.
Yusuf Ozturk and Hüseyin Abut. System of Associative Relationship (SOAR). Proceedings of ASILOMAR’97. Pacific Grove, CA. (1997).
H. Rieger. Storing an extensive number of grey-toned patterns in a neural network using multistate neurons. Journal of Physics. A23, L1273–79 (1990).
F.Y. Wu. The Potts Model Reviews of Modern Physics. 54(1), (1982).
Jacek M. Zurada, Ian Cloete and Etienne van der Poel. Generalized Hopfield networks for associative memories withm ulti-valued stable states. Neurocomputing 13, 135–149 (1996).
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
Mérida-Casermeiro, E., Muñoz-Pérez, J., García-Bernal, M. (2002). An Associative Multivalued Recurrent Network. In: Garijo, F.J., Riquelme, J.C., Toro, M. (eds) Advances in Artificial Intelligence — IBERAMIA 2002. IBERAMIA 2002. Lecture Notes in Computer Science(), vol 2527. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-36131-6_52
Download citation
DOI: https://doi.org/10.1007/3-540-36131-6_52
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-00131-7
Online ISBN: 978-3-540-36131-2
eBook Packages: Springer Book Archive