Abstract
Most models of neural associative memory have used networks with full connectivity. However, this seems unrealistic from a neuroanatomical perspective and a VLSI implementation viewpoint. In this study, we built a new associative memory network based on the Watts-Strogatz model. The results indicate that this new network can recall the memorized patterns even with only a small fraction of total connections and is more sufficient than other networks with sparse topologies, such as randomly connected network and regularly network.
Project supported by National Natural Science Foundation of China (No. 60375011, 60575028) and Program for New Century Excellent Talents in University(NCET-04-0560).
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
Hopfield, J.J.: Neural networks and physical systems with emergent collective computational abilities. Proc. Natl. Acad. Sci. USA 79, 2445–2458 (1982)
Amit, D.J.: Modeling brain function: the world of attractor neural networks. Cambridge University Press, Cambridge (1989)
Braitenberg, V., Schüz, A.: Cortex: Statistics and Geometry of Neuronal Connectivity. Springer, Berlin (1998)
Newman, M.E.J.: Models of the Small World. Journal of Statistical Physics 101(3/4), 819–841 (2000)
Venkatesh, S.: Robustness in neural computation: Random graphs and sparsity. IEEE Trans. Inf.Theory 38, 1114–1119 (1992)
Komlohs, J.: Effect of connectivity in an associative memory model. J. Comput. System Sciences 47, 350–373 (1993)
Levy, N., Ruppin, E.: Associative memory in a multi-modular network. Neural Comput. 11, 1717–1737 (1999)
Watts, D., Strogatz, S.: Collective Dynamics of ‘small-world’ networks. Nature 393, 440–442 (1998)
Shefi, O., et al.: Morphological characterization of in vitro neuronal networks. Physical Review E 66(021905) (2002)
Bohland, J.W., Minai, A.A.: Efficient associative memory using small-world architecture. Neurocomputing 38–40, 489–496 (2001)
Davey, N., Christianson, B., Adams, R.: High Capacity Associative Memories and Small World Networks. In: Proc. of IEEE IJCNN 2004, Budapest, Hungary, July 25-29 (2004)
Milgram, S.: The small-world problem. Psychol. Today 2, 60–67 (1967)
Bollobás, B.: Random Graphs. Academic Press, New York (1985)
Chua, L.O., Yang, L.: Cellular neural network: applications. IEEE Transactions on Circuits and Systems 35, 1273–1290 (1988)
McEliece, R.J., Posner, E.C., Rodemich, E.R., Venkatesh, S.S.: The capacity of the Hopfield associative memory. IEEE Trans. on Information Theory 33, 461–482 (1987)
Stauffer, D., et al.: Efficient Hopfield pattern recognition on a scale-free neural network. European Physical Journal B 32(3), 395–399 (2003)
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
Zhi, X., Jun, G., Jing, S., Yajin, Z. (2006). Associative Memory with Small World Connectivity Built on Watts-Strogatz Model. In: Jiao, L., Wang, L., Gao, Xb., Liu, J., Wu, F. (eds) Advances in Natural Computation. ICNC 2006. Lecture Notes in Computer Science, vol 4221. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11881070_19
Download citation
DOI: https://doi.org/10.1007/11881070_19
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-45901-9
Online ISBN: 978-3-540-45902-6
eBook Packages: Computer ScienceComputer Science (R0)