Neural Networks Model for Optimization an Study on Isomorphism Discernment

Abstract:

An artificial neural network is composed of large number of simple processing elements by direct links named connections, the benefits of neural networks extend beyond the high computation rates by massive parallelism. Optimization problems could be transferred into a feedback network, the network interconnects the neurons with a feedback path. Graphs isomorphism discernment is one of the most important and difficult issues in graphs theory based structures design. To solve the problem, a Hopfield neural networks (HNN) model is presented in this paper. The solution of HNN is design as a permutation matrix of two graphs, and some operators are improved to prevent premature convergence. It is concluded that the algorithm presented here is efficient for large-scale graphs isomorphism problem and other NP-complete optimization issues.

• Periodical: Advanced Materials Research (Volumes 156-157)
• Pages: 492-495
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.156-157.492
• Online since: October 2010
• Authors: Miao Zhang, Ning Bo Liao, Chen Zhou
• Keywords: Graph Isomorphism, Hopfield Neural Networks, Intelligent Design, Kinematic Structure Enumeration

References

[1] Y. J Shan, et al: IEEE Trans. Syst. Man Cybern Vol. 4 (1974), p.313.

[2] C.S. Tang and, T. Liu: Machines and Robotics Vol. 15 (1988), p.147.

[3] Z.Y. Yang, M.L. Zhang and Y. Zhang: J. of Beijing University of Chemical Technology Vol. 29 (2002), 75.

[4] V.V. Kureichik and V.M. Kureichik: IEEE International Conference on Artificial Intelligence Systems (2002).

[5] P. Yang, N.B. Liao, B. Yang, J.N. Ding and J.C. Yang: The International Journal of Advanced Manufacturing Technology Vol. 31 (2007), p.841.

[6] P. Yang, Z.H. Pei, N.B. Liao and B. Yang: Eng. Comput. (Lond. ) Vol. 23 (2007), p.49.

[7] L.W. Tsai: CRC Press, Boca Raton, FL (2000).