Abstract
High-order neural networks can be considered as an expansion of Hopfield neural networks, and have stronger approximation property and faster convergence rate. However, in practice high order network is seldom to be used to solve combinatorial optimization problem. In this paper crossbar switch problem, which is an NP-complete problem, is used as an example to demonstrate how to use high order discrete Hopfield neural network to solve engineering optimization problems. The construction method of energy function and the neural computing algorithm are presented. It is also discussed the method how to speed the convergence and escape from local minima. Experimental results show that high order network has a quick convergence speed, and outperforms the traditional discrete Hopfield network.
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., Tank, D.W.: Neural computation of decisions in optimization problems. Biol. Cybern. 52(1), 141–152 (1985)
Galán-MarÃn, G., et al.: A Study into the Improvement of Binary Hopfield Networks for Map Coloring. In: Beliczynski, B., et al. (eds.) ICANNGA 2007. LNCS, vol. 4432, pp. 98–106. Springer, Heidelberg (2007)
Wang, J.: A Memetic Algorithm with Genetic Particle Swarm Optimization and Neural Network for Maximum Cut Problems. In: Li, K., Fei, M., Irwin, G.W., Ma, S. (eds.) LSMS 2007. LNCS, vol. 4688, pp. 297–306. Springer, Heidelberg (2007)
Wang, J., Tang, Z.: An improved optimal competitive Hopfield network for bipartite subgraph problems. Neurocomputing 61(5), 413–419 (2004)
Thangavel, P., Gladis, D.: Hopfield Hysteretic Hopfield network with dynamic tunneling for crossbar switch and N-queens problem. Neurocomputing 70, 2544–2551 (2007)
Xia, G., Tang, Z., Li, Y., Wang, J.: A binary Hopfield neural network with hysteresis for large crossbar packet-switches. Neurocomputing 67, 417–425 (2005)
Troudet, T.P., Walters, S.M.: Neural Network Architecture for Crossbar Switch Control. IEEE Trans. Circuits Syst. 38(1), 42–56 (1991)
W. Noguchi, C.-K. Pham.: A Proposal to Solve N-Queens Problems Using Maximum Neuron Model with A Modified Hill-Climbing Term. Neural Networks, IJCNN, 2679–2683 (2006)
Xu, B., Liu, X., Teoc, K.L.: Global exponential stability of impulsive high-order Hopfield type neural networks with delays. Computers and Mathematics with Applications 57(3), 1959–1967 (2009)
Yi, X., Shao, J., Yu, Y., et al.: Global exponential stability of impulsive high-order Hopfield type neural networks with delays. Journal of Computational and Applied Mathematics 219(3), 216–222 (2008)
Ou, C.: Anti-periodic solutions for high-order Hopfield neural networks. Computers and Mathematics with Applications 56(3), 1838–1844 (2008)
Gopalsamy, K.: Learning dynamics in second order networks. Nonlinear Analysis: Real World Applications 8(9), 688–698 (2007)
Cheung, K., Lee, T.: On the Convergence of Neural Network for higher Order Programming. IJCNN 2, 1507–1511 (1993)
Foo, Y.P.S., Szu, H.: Solving Large-Scale Optimization Problems by Divide-and-Conquer Neural Networks. IJCNN 1, 507–511 (1989)
Lo, J.T.-H.: A New Approach to Global Optimization and its Applications to Neural Networks. Neural Networks 2(5), 367–373 (1992)
Wang, L.P., Li, S., Tian, F.Y., Fu, X.J.: A Noisy Chaotic Neural Network for Solving Combinatorial Optimization Problems: Stochastic Chaotic Simulated Annealing. IEEE Trans. on Sys., Man, Cybern., Part B - Cybern. 34(5), 2119–2125 (2004)
Amartur, S.C., Piraino, D., Takefuji, Y.: Optimization Neural Networks for the Segmentation of Magnetic Resonance Images. IEEE Trans. on Medical Imaging 11(2), 215–220 (1992)
Salcedo-Sanz, S., Yao, X.: A hybrid Hopfield network-genetic algorithm approach for the terminal assignment problem. IEEE Trans on Systems, Man and Cybernetics 34(6), 2343–2353 (2004)
Li, Y.M., et al.: An Improvement to Ant Colony Optimization Heuristicp. In: Sun, F., Zhang, J., Tan, Y., Cao, J., Yu, W. (eds.) ISNN 2008, Part I. LNCS, vol. 5263, pp. 816–825. Springer, Heidelberg (2008)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2010 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Ding, Y., Dong, L., Wang, L., Wu, G. (2010). A High Order Neural Network to Solve Crossbar Switch Problem. In: Wong, K.W., Mendis, B.S.U., Bouzerdoum, A. (eds) Neural Information Processing. Models and Applications. ICONIP 2010. Lecture Notes in Computer Science, vol 6444. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-17534-3_85
Download citation
DOI: https://doi.org/10.1007/978-3-642-17534-3_85
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-17533-6
Online ISBN: 978-3-642-17534-3
eBook Packages: Computer ScienceComputer Science (R0)