Design Chaotic Neural Network from Discrete Time Feedback Function

Abstract:

The goal of this paper is to give a universal design methodology of a Chaotic Neural Net-work (CNN). By appropriately choosing self-feedback, coupling functions and external stimulus, we have succeeded in proving a dynamical system defined by discrete time feedback equations possess-ing interesting chaotic properties. The sufficient conditions of chaos are analyzed by using Jacobian matrix, diagonal dominant matrix and Lyapunov Exponent (LE). Experiments are also conducted un-der a simple data set. The results confirm the theorem's correctness. As far as we know, both the experimental and theoretical results presented here are novel.

• Periodical: Applied Mechanics and Materials (Volume 339)
• Pages: 366-371
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.339.366
• Online since: July 2013
• Authors: Jin Sheng Ren, Guang Chun Luo, Ke Qin
• Keywords: Chaotic Neural Networks, Nonlinear Dynamical Systems, Nonlinear Dynamics

References

[1] K. Aihara, T. Takabe, and M. Toyoda, "Chaotic neural networks,'' Physics Letters A, vol.144, no.6-7, p.333--340, 1990.

DOI: 10.1016/0375-9601(90)90136-c

[2] M. Adachi and K. Aihara, "Associative dynamics in a chaotic neural network,'' Neural Networks, vol.10, no.1, p.83--98, 1997.

DOI: 10.1016/s0893-6080(96)00061-5

[3] K. Qin and B.J. Oommen, "Adachi-like chaotic neural networks requiring linear-time computations by enforcing a tree-shaped topology,'' IEEE Transactions on Neural Networks, vol.20, no.11, p.1797--1809, 2009.

DOI: 10.1109/tnn.2009.2030582

[4] K. Qin and B.J. Oommen, "Networking logistic neurons can yield chaotic and pattern recognition properties,'' IEEE International Conference on Computational Intelligence for Measure Systems and Applications, Ottawa, Ontario, Canada, p.134--139, 2011.

DOI: 10.1109/cimsa.2011.6059914

[5] K. Qin and B.J. Oommen, "The entire range of chaotic pattern recognition properties possessed by the adachi neural network,'' Intelligent Decision Technologies, vol.6, p.27--41, 2012.

DOI: 10.3233/idt-2012-0120

[6] G. Luo, J. Ren and K. Qin, "Dynamical Associative Memory: The Properties of the New Weighted Chaotic Adachi Neural Network,'' IEICE Transactions on Information and Systems, vol.95-D, no.8, p.2158--2162, 2012.

DOI: 10.1587/transinf.e95.d.2158

[7] E. Hiura and T. Tanaka, "A chaotic neural network with duffing's equation,'' Proceedings of International Joint Conference on Neural Networks, Orlando, Florida, USA, p.997--1001, 2007.

DOI: 10.1109/ijcnn.2007.4371094

[8] T. Tanaka and E. Hiura, "Dynamical behavior of a chaotic neural network and its applications to optimization problem,'' The International Joint Conference On Neural Network, Montreal Canada, p.753--757, 2005.

DOI: 10.1109/ijcnn.2005.1555946

[9] J. Cao and J. Lu, "Adaptive synchronization of neural networks with or without time-varying delays,'' Chaos, vol.16, no.1, 2006.

[10] D. Calitoiu, B.J. Oommen, and D. Nussbaum, ``Periodicity and stability issues of a chaotic pattern recognition neural network,'' Pattern Analysis and Applications, vol.10, no.3, p.175--188, 2007.

DOI: 10.1007/s10044-007-0060-3

[11] G. Chen and D. Lai, "Feedback control of lyapunov exponents for discrete-time dynamical systems,'' International Journal of Bifurcation and Chaos in Applied Sciences and Engineering, vol.6, no.7, p.1341--1350, 1996.

DOI: 10.1142/s021812749600076x