Block Activity in Metric Neural Networks
Commenced in January 2007
Frequency: Monthly
Edition: International
Paper Count: 32769
Block Activity in Metric Neural Networks

Authors: Mario Gonzalez, David Dominguez, Francisco B. Rodriguez

Abstract:

The model of neural networks on the small-world topology, with metric (local and random connectivity) is investigated. The synaptic weights are random, driving the network towards a chaotic state for the neural activity. An ordered macroscopic neuron state is induced by a bias in the network connections. When the connections are mainly local, the network emulates a block-like structure. It is found that the topology and the bias compete to influence the network to evolve into a global or a block activity ordering, according to the initial conditions.

Keywords: Block attractor, random interaction, small world, spin glass.

Digital Object Identifier (DOI): doi.org/10.5281/zenodo.1335232

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1287

References:


[1] Dale Purves
[et al.], Neuroscience, 3rd ed. Sinauer Associates, Inc., 2004.
[2] D. J. Amit, Modelling Brain Function: The World of Attractor Neural Networks, Cambridge University Press, 1989.
[3] Watts, D. J. and Strogatz, S. H., Collective dynamics of -small-world- networks, Nature, 393-6684, pages 440-442, 1998.
[4] C. Li and G. Chen, Stability of a neural network model with small-world connections, Phys.Rev.E68, 52901-4 (2003).
[5] D. Dominguez and K. Koroutchev and E. Serrano and F. B. Rodriguez, Information and topology in attractor neural network, Neural Computation, 19(4), 956-73, 2007.
[6] K. Koroutchev and E. Koroutcheva, Bump formation in a binary attractor neural network, Phys.Rev.E73, 026107 (2006).
[7] J. P. L. Hatchett, N. S. Skantzos, and T. Nikoletopoulos, Dynamic rewiring in small world networks, Phys.Rev.E72, 066105, 2005.
[8] T. Nikoletopoulos, A. C. C. Coolen, I. Perez Castillo, N. S. Skantzos, J. P. L. Hatchett and B. Wemmenhove, Replicated transfer matrix analysis of Ising spin models on small world lattices, J. Phys. A: Math. Gen. 37, pages 6455-64754, 2004.
[9] D. R. Paula, A. D. Araujo, J. S. Andrade Jr., H. J. Herrmann and J. A. C. Gallas, Periodic neural activity induced by network complexity, Phys. Rev. E 74, 017102, 2006.
[10] G. Morelli, G. Abramson and M. N. Kuperman, Associative memory on a small-world neural network, The European Physical Journal B 38-3, pages 495-500, 2004.
[11] Y. Roudi and A. Treves, Localized activity profiles and storage capacity of rate-based autoassociative networks, Phys. Rev. E 73, 061904, 2006.
[12] D. Dominguez, K. Korutchev, E. Serrano and F. Rodriguez, Mutual Information and Neural Network Topology 1: Asymmetric Neural Network, LNCS 3173, pages 14-19, 2004.
[13] M. Gonzalez, D. Dominguez and F. B. Rodriguez, Learning block patterns with metric neural network, In: Proc. ICNN, Cairo, 2008.