Abstract
Based on chaotic neural network, a multiple chaotic neural network algorithm combining two different chaotic dynamics sources in each neuron is proposed. With the effect of self-feedback connection and non-linear delay connection weight, the new algorithm can contain more powerful chaotic dynamics to search the solution domain globally in the beginning searching period. By analyzing the dynamic characteristic and the influence of cooling schedule in simulated annealing, a flexible parameter tuning strategy being able to promote chaotic dynamics convergence quickly is introduced into our algorithm. We show the effectiveness of the new algorithm in two difficult combinatorial optimization problems, i.e., a traveling salesman problem and a maximum clique problem.
Similar content being viewed by others
References
Aihara K (2002) Chaos engineering and its application to parallel distributed processing with chaotic neural networks. Proc IEEE 90:919–930
Cao Y, Liu S, Liu X (2006) Optimization of SF/sub 6/ circuit breaker based on chaotic neural network. IEEE Trans Magn 42:1151–1154
Chen L, Aihara K (1995) Chaotic simulated annealing by a neural network model with transient chaos. Neural Netw 8(6):915–930
Hansel D, Sompolinsky H (1992) Synchronization and computation in a chaotic neural network. Phys Rev Lett 68:5
Hasegawa M, Ikeguchi T, Matozaki T, Aihara K (1995) Solving combinatorial optimization problems by nonlinear neural dynamics. In: Proceedings of ICNN95 - international conference on neural networks, pp 3140–3145
He Y (2002) Chaotic simulated annealing with decaying chaotic noise. IEEE Trans Neural Netw 13(6):1526–1531
Hopfield JJ, Tank DW (1985) Neural computation of decisions in optimization problems. Biol Cybern 52:141–152
Hopfield JJ, Tank DW (1986) Computing with neural circuits: a model. Science 233:624–633
Jagota A (1995) Approximating maximum clique with a Hopfield network. IEEE Trans Neural Netw 6(3):724–735
Klotz A, Brauer K. (1999) A small-size neural network for computing with strange attractors. Neural Netw 12:601–607
Kwok T, Smith KA (2000) Experimental analysis of chaotic neural network models for combinatorial optimization under a unifying framework. Neural Netw 13:731–744
Lin JS (2001) Annealed chaotic neural network with nonlinear self-feedback and its application to clustering problem. Pattern Recognit 34:1093–1104
Lysetskiy M, Zurada JM (2004) Bifurcating neuron: computation and learning. Neural Netw 17:225–232
Nozawa H (1992) A neural-network model as a globally coupled map and applications based on chaos. Chaos 2(3):377–386
Ohta M (2002) Chaotic neural networks with reinforced self-feedbacks and its application to N-Queen problem. Math Comput Simul 59(4):305–317
Potapov A, Ali MK (2000) Robust chaos in neural networks. Phys Lett A 277:310–322
Potvin JY (1993) The traveling salesman problem: a neural network perspective. ORSA J Comput 5:328–348
Tokuda I, Nagashima T, Aihara K (1997) Global bifurcation structure of chaotic neural networks and its application to traveling salesman problems. Neural Netw 10:1673–1690
Tokuda I, Aihara K, Nagashima T (1998) Adaptive annealing for chaotic optimization. Phys Rev E 58(4):5157–5160
Wang L, Smith K (1998) On chaotic simulated annealing. IEEE Trans Neural Netw 9:716–718
Wang L, Li S, Tian F, Fu X (2004) A noisy chaotic neural network for solving combinatorial optimization problems: stochastic Chaotic simulated annealing. IEEE Trans Syst Man Cybern Part B Cybern 34(5):2119–2125
Wang LP, Liu W, Shi H (2008) Noisy chaotic neural networks with variable thresholds for the frequency assignment problem in satellite communications. IEEE Trans Syst Man Cybern Part C Rev Appl 38(2):209–217
Wang LP, Liu W, Shi H (2009) Delay-constrained multicast routing using the noisy chaotic neural networks. IEEE Trans Comput 58(1):82–89
Xu YQ, Sun M, Zhang JH (2006) A model of wavelet chaotic neural network with applications in optimization. In: Proceedings 6th World Congr. Intell. Control Autom, China 1:2901–2905
Yang G, Tang Z, Zhang Z, Zhu Y (2007) A flexible annealing chaotic neural network to maximum clique problem. Int J Neural Syst 17(3):183–192
Yang G., Yi J, Vairappan C, Tang Z (2008) A flexible annealing strategy for chaotic neural network to maximum clique problem. Int J Innov Comput Inf Control 4(4):981–993
Yi J, Yang G, Zhang Z, Tang Z (2009) An improved elastic net method with time-dependent parameters for traveling salesman problem. Int J Innov Comput Inf Control 5(4):1089–1100
Zhao L, Sun M, Cheng J, Xu Y (2009) A novel chaotic neural network with the ability to characterize local features and its application. IEEE Trans Neural Netw 20(4)
Zhou CS, Chen T (2000) Chaotic neural networks and chaotic annealing. Neurocomputing 30:293–300
Acknowledgments
This research was partially supported by the grants from the Natural Science Foundation of China (No. 61003205, No. 71001103); Zhejiang Provincial Natural Science Foundation of China (No. Y1101062); the Fundamental Research Funds for the Central Universities,and the Research Funds of Renmin University of China (No. 10XNF036).
Author information
Authors and Affiliations
Corresponding author
Additional information
Communicated by Y. Jin.
Rights and permissions
About this article
Cite this article
Yang, G., Yi, J. Dynamic characteristic of a multiple chaotic neural network and its application. Soft Comput 17, 783–792 (2013). https://doi.org/10.1007/s00500-012-0948-8
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00500-012-0948-8