Abstract
Recently, bump formations in attractor neural networks with distance dependent connectivities has become of increasing interest for investigation in the field of biological and computational neuroscience. Although the distance dependent connectivity is common in biological networks, a common fault of these network is the sharp drop of the number of patterns p that can remembered, when the activity changes from global to bump-like, than effectively makes these networks low effective.
In this paper we represent a bump-based recursive network specially designed in order to increase its capacity, which is comparable with that of randomly connected sparse network. To this aim, we have tested a selection of 700 natural images on a network with N = 64K neurons with connectivity per neuron C. We have shown that the capacity of the network is of order of C, that is in accordance with the capacity of highly diluted network. Preserving the number of connections per neuron, a non-trivial behavior with the radius of the connectivity has been observed. Our results show that the decrement of the capacity of the bumpy network can be avoided.
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
Roudi, Y., Treves, A.: JSTAT, P07010, 1 (2004)
Roudi, Y., Treves, A.: cond-mat/0505349
Koroutchev, K., Korutcheva, E.: Preprint ICTP, Trieste, Italy, IC/2004/91, 1, (2004); Koroutchev, K., Korutcheva, E.: Central Europ. J.Phys. 3, 409, (2005); Koroutchev, K., Korutcheva, E.: Phys. Rev. E 73(2) (2006)
Anishchenko, A., Bienenstock, E., Treves, A.: q-bio.NC/0502003
Breitenberg, V., Schulz, A.: Anatomy of the Cortex. Springer, Berlin (1991)
Watts, D.J., Strogatz, S.H.: Nature 393, 440 (1998)
Watts, D.J.: Small Worlds: The Dynamics of Networks Between Order and Randomness (Princeton Review in Complexity). Princeton University Press, Princeton (1999)
Hopfield, J.: Proc. Natl. Acad. Sci. USA, 79, 2554 (1982)
Tsodyks, M., Feigel’man, M.: Europhys.Lett. 6, 101 (1988); Stat. Phys., 14, 565 (1994)
Amit, D., Gutfreund, H., Sompolinsky, H.: Ann. Phys. 173, 30–67 (1987)
van Hateren, J.H., van der Schaaf, A.: Independent component filters of natural images compared with simple cells in primary visual cortex. Proc. R. Soc. Lond. B 265, 359–366 (1998)
Koroutchev, K., Korutcheva, E.: In the Proceedings of the 9th Granada Seminar on Computational and Statistical Physics, AIP (2006)
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
Koroutchev, K., Korutcheva, E. (2006). Improved Storage Capacity of Hebbian Learning Attractor Neural Network with Bump Formations. In: Kollias, S.D., Stafylopatis, A., Duch, W., Oja, E. (eds) Artificial Neural Networks – ICANN 2006. ICANN 2006. Lecture Notes in Computer Science, vol 4131. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11840817_25
Download citation
DOI: https://doi.org/10.1007/11840817_25
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-38625-4
Online ISBN: 978-3-540-38627-8
eBook Packages: Computer ScienceComputer Science (R0)