A New Neural Network Structure: Node-to-Node-Link Neural Network

S. H. Ling

.

DOI: 10.4236/jilsa.2010.21001                

Abstract

This paper presents a new neural network structure and namely node-to-node-link neural network (N-N-LNN) and it is trained by real-coded genetic algorithm (RCGA) with average-bound crossover and wavelet mutation [1]. The N-N-LNN exhibits a node-to-node relationship in the hidden layer and the network parameters are variable. These characteristics make the network adaptive to the changes of the input environment, enabling it to tackle different input sets distributed in a large domain. Each input data set is effectively handled by a corresponding set of network parame-ters. The set of parameters is governed by other nodes. Thanks to these features, the proposed network exhibits better learning and generalization abilities. Industrial application of the proposed network to hand-written graffiti recognition will be presented to illustrate the merits of the network.

Keywords

Genetic Algorithm, Hand-Written Graffiti Recognition, Neural Network

Conflicts of Interest

The authors declare no conflicts of interest.

References

[1]	S. H. Ling and F. H. F Leung, “An improved genetic algorithm with average-bound crossover and wavelet mutation operations,” Soft Computing, Vol. 11, No.1, pp. 7–31, January 2007.
[2]	F. M. Ham and I. Kostanic, “Principles of neurocomputing for science & engineering,” McGraw Hill, 2001.
[3]	R. C. Bansal and J. C. Pandey, “Load forecasting using artificial intelligence techniques: A literature survey,” International Journal of Computer Applications in Technology, Vol. 22, Nos. 2/3, pp. 109–119, 2005.
[4]	S. H. Ling, F. H. F. Leung, H. K. Lam, and P. K. S. Tam, “Short-term electric load forecasting based on a neural fuzzy network,” IEEE Transactions on Industrial Electronics, Vol. 50, No. 6, pp. 1305–1316, December 2003.
[5]	S. H. Ling, F. H. F. Leung, L. K. Wong, and H. K. Lam, “Computational intelligence techniques for home electric load forecasting and balancing,” International Journal Computational Intelligence and Applications, Vol. 5, No. 3, pp. 371–391, 2005.
[6]	F. H. F. Leung, H. K. Lam, S. H. Ling, and P. K. S. Tam, “Tuning of the structure and parameters of neural network using an improved genetic algorithm,” IEEE Transactions on Neural Networks, Vol. 14, No. 1, pp. 79–88, January 2003.
[7]	K. F. Leung, F. H. F. Leung, H. K. Lam, and S. H. Ling, “On interpretation of graffiti digits and commands for eBooks: Neural-fuzzy network and genetic algorithm app- roach,” IEEE Transactions on Industrial Electronics, Vol. 51, No. 2, pp. 464–471, April 2004.
[8]	D. R. Lovell, T. Downs, and A. C. Tsoi, “An evaluation of the neocognitron,” IEEE Transactions on Neural Networks, Vol. 8, No. 5, pp. 1090–1105, September 1997.
[9]	Z. Michalewicz, “Genetic algorithm + data structures = evolution programs,” 2nd extended edition, Springer-Verlag, 1994.
[10]	C. A. Perez, C. A. Salinas, P.A. Estévez, and P. M. Valenzuela, “Genetic design of biologically inspired receptive fields for neural pattern recognition,” IEEE Transactions on Systems, Man, and Cybernetics — Part B: Cybernetics, Vol. 33, No. 2, pp. 258–270, April 2003.
[11]	B. Widrow and M. A. Lehr, “30 years of adaptive neural networks: Perceptron, madaline, and backpropagation,” Proceedings of the IEEE, Vol. 78, No. 9, pp. 1415–1442, September 1990.
[12]	R. Buse, Z. Q. Liu, and J. Bezdek, “Word recognition using fuzzy logic,” IEEE Transactions on Fuzzy Systems, Vol. 10, No. 1, February 2002.
[13]	L. Davis, “Handbook of genetic algorithms,” NY: Van Nostrand Reinhold, 1991.
[14]	X. Yao, “Evolving artificial networks,” Proceedings of the IEEE, Vol. 87, No. 7, pp. 1423–1447, 1999.
[15]	P. D. Gader and M. A. Khabou, “Automatic feature generation for handwritten digit recognition,” IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 18, No. 12, pp. 1256–1261, December 1996.
[16]	L. Holmstr?m, P. Koistinen, J. Laaksonen, and E. Oja, “Neural and statistical classifiers — Taxonomy and two case studies,” IEEE Transactions on Neural Networks, Vol. 8, No. 1, pp. 5–17, January 1997.
[17]	J. Zhang, G. G. Walter, Y. Miao, and W. W. N. Lee, “Wavelet neural networks for function learning,” IEEE Transactions on Signal Processing, Vol. 43, No. 6, pp. 1485–1497, June 1995.
[18]	B. Zhang, M. Fu, H. Yan, and M. A. Jabri, “Handwritten digit recognition by adaptive-subspace self-organizing map (ASSOM),” IEEE Transactions on Neural Networks, Vol. 10, No. 4, pp. 939–945, July 1997.
[19]	C. K. Ho and M. Sasaki, “Brain-wave bio potentials based mobile robot control: Wavelet-neural network pattern recognition approach,” in Proceedings IEEE International Conference on System, Man, and Cybernetics, Vol. 1, pp. 322–328, October 2001.
[20]	S. Yao, C. J. Wei, and Z. Y. He, “Evolving wavelet neural networks for function approximation,” Electron Letter, Vol.32, No.4, pp. 360–361, February 1996.
[21]	Q. Zhang and A. Benveniste, “Wavelet networks,” IEEE Transactions on Neural Networks, Vol. 3, No. 6, pp. 889–898, November 1992.