A New Small-World Neural Network with its Performance on Fault Tolerance

Abstract:

Many artificial neural networks are the simple simulation of brain neural network’s architecture and function. However, how to rebuild new artificial neural network which architecture is similar to biological neural networks is worth studying. In this study, a new multilayer feedforward small-world neural network is presented using the results form research on complex network. Firstly, a new multilayer feedforward small-world neural network which relies on the rewiring probability heavily is built up on the basis of the construction ideology of Watts-Strogatz networks model and community structure. Secondly, fault tolerance is employed in investigating the performances of new small-world neural network. When the network with connection fault or neuron damage is used to test the fault tolerance performance under different rewiring probability, simulation results show that the fault tolerance capability of small-world neural network outmatches that of the same scale regular network when the fault probability is more than 40%, while random network has the best fault tolerance capability.

• Periodical: Advanced Materials Research (Volume 629)
• Pages: 719-724
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.629.719
• Online since: December 2012
• Authors: Xiao Hu Li, Feng Xu, Jin Hua Zhang, Su Nan Wang
• Keywords: Complex Network, Fault Tolerance, Neural Network (NN), Small-World

References

[1] Basheer IA, Hajmeer M. Artificial neural networks: fundamentals, computing, design, and application. J of Metho Microbio 2000; 43: 3–31.

DOI: 10.1016/s0167-7012(00)00201-3

[2] Xia YS, Wang JA. general methodology for designing globally convergent optimization neural network. IEEE Trans on Neural Network 1998; 9(6): 1331–1343.

DOI: 10.1109/72.728383

[3] Monirul I, Abdus S, Faijul A, Yao X, Kazuyuki M. A New Adaptive Merging and Growing Algorithm for Designing Artificial Neural Networks. IEEE Trans on System, Man, and Cybernetics—Part B: Cybernetics 2009; 39(3): 705–721.

DOI: 10.1109/tsmcb.2008.2008724

[4] Hu SG, Liao XX, Mao XR. Stochastic Hopfield neural network. J of Phy A: Math and Gen 2003; 36(9): 2235–2249.

DOI: 10.1088/0305-4470/36/9/303

[5] Sporns O, Honey CJ. Small worlds inside big brains. Proce of National Academy of Sci 2006; 103(51): 19219–19220.

DOI: 10.1073/pnas.0609523103

[6] Horwitz B. The elusive concept of brain connectivity. NeuroImage 2003; 19: 466–470.

DOI: 10.1016/s1053-8119(03)00112-5

[7] Watts DJ, Strogatz SH. Collective dynamics of small-world network. Nature 1998; 393(4): 440–442.

DOI: 10.1038/30918

[8] Newman MEJ. The architecture and function of complex network. SIAM Review 2003; 45(2): 167–256.

[9] Bassett DS, Bullmore E. Small-world brain network. Neuroscientist 2006; 12(6): 512–523.

DOI: 10.1177/1073858406293182

[10] Girvan M, Newman MEJ. Community structure in social and biological networks. Proceedings of National Academy of Science 2002; (99)12: 7821–7826.

DOI: 10.1073/pnas.122653799

[11] Simard D, Nadeau L, Kroger H. Faster learning in small-world neural network. Phy Letters A 2005; 336(1): 8–15.

[12] Kleinberg J. Navigation in a small world. Nature 2000; 406: 845.

[13] Rumelhart DE, Hinton GE, Willianms RJ. Learning representations by back-propagation error. Nature 1986; 323(9): 303–314.