Tuning the Structure and Parameters of a Neural Network by Using Cooperative Quantum Particle Swarm Algorithm

Abstract:

In this paper, a cooperative quantum genetic algorithm-particle swarm algorithm (CQGAPSO) is applied to tune both structure and parameters of a feedforward neural network (NN) simultaneously. In CQGAPSO algorithm, QGA is used to optimize the network structure and PSO algorithm is employed to search the parameters space. The amplitude-based coding method and cooperation mechanism improve the learning efficiency, approximation accuracy and generalization of NN. Furthermore, the ill effects of approximation ability caused by redundant structure of NN are eliminated by CQGAPSO. The experimental results show that the proposed method has better prediction accuracy and robustness in forecasting the sunspot numbers problems than other training algorithms in the literatures.

• Periodical: Applied Mechanics and Materials (Volumes 48-49)
• Pages: 1328-1332
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.48-49.1328
• Online since: February 2011
• Authors: Qi Feng Tang, Liang Zhao, Rong Bin Qi, Hui Cheng, Feng Qian
• Keywords: CQGAPSO, Neural Network (NN), Particle Swarm Optimization Algorithm (PSO), Quantum Genetic Algorithm

References

[1] L.S. Shu, S.Y. Ho, S.J. Ho, Tuning the structure and parameters of a neural network using an orthogonal simulated annealing algorithm, 2009 Joint conferences on Pervasive Computing, 789-192, (2009).

DOI: 10.1109/jcpc.2009.5420077

[2] G. Yu, G. Li, Y. Bai, X. Jin, Tuning of the structure and parameters of wavelet Neural network using improved chaotic PSO, Chinese Control Conference, 228-232, (2007).

DOI: 10.1109/chicc.2006.4347595

[3] C. Xiao, Z. Cai, Y. Wang, X. Liu, Tuning of the strcture and parameters of a neural network using a good points set evolutionary strategy, The 9th International conference for Young Computer Scientists, 1749-1754, (2008).

DOI: 10.1109/icycs.2008.187

[4] H. F. Leung, H. K. Lam, S. H. Ling, K. S. Tam, Tuning of the structure and parameters of neural network using an improved genetic algorithm, Proc. 27th Annu. Conf. IEEE Industrial Electronics Society, 25-30, (2001).

DOI: 10.1109/iecon.2001.976448

[5] J. T. Tsai, J. H. Chou, T. K. Liu, Tuning the structure and parameters of a neural network bu using Hybrid Taguchi-Genetic Algorithm, IEEE Transactions on Neural Network, 17(1): 69-80, (2006).

DOI: 10.1109/tnn.2005.860885

[6] L. Zhao, F. Qian, Tuning the structure and parameters of a neural network using cooperative binary-real particle swarm optimization. Expert Systems with Applications (2010), doi: 10. 1016/j. eswa. 2010. 09. 154.

DOI: 10.1016/j.eswa.2010.09.154

[7] A. Narayanan, M. Moore, Quantum-inspired genetic algorithms, Proceeding of IEEE Press International Conference on Evolutionary Computation. Nagoya: EEE Press, 1-66, (1996).

[8] J. Kennedy, R. Eberhart, Y. Shi. Swarm intelligence. Morgan Kaufmann, (2001).

[9] M. A. Potter, K. A. De Jong, A cooperative coevolutionary approach to function optimization, in The Third Parallel Problem Solving From Nature, 249-257, Springer-Verlag, Berlin, (1994).

DOI: 10.1007/3-540-58484-6_269

[10] M. A. Potter, K. A. De Jong, Cooperative coevolution: An architecture for evolving coadapted subcomponents. Evolutionary Computation, 8(1): 1-29, (2000).

DOI: 10.1162/106365600568086