×

zbMATH — the first resource for mathematics

Training algorithm for radial basis function neural network based on quantum-behaved particle swarm optimization. (English) Zbl 1185.68545
Summary: Radial basis function (RBF) networks are widely applied in function approximation, system identification, chaotic time series forecasting, etc. To use a RBF network, a training algorithm is absolutely necessary for determining the network parameters. The existing training algorithms, such as orthogonal least squares algorithm, clustering and gradient descent algorithm, have their own shortcomings respectively. In this paper, we propose a training algorithm based on a novel population-based evolutionary technique, quantum-behaved particle swarm optimization (QPSO), to train RBF neural network. The proposed QPSO-trained RBF network was tested on non-linear system identification problem and chaotic time series forecasting problem, and the results show that it can identify the system and forecast the chaotic time series more quickly and precisely than that trained by the particle swarm algorithm.
MSC:
68T05 Learning and adaptive systems in artificial intelligence
68T20 Problem solving in the context of artificial intelligence (heuristics, search strategies, etc.)
92B20 Neural networks for/in biological studies, artificial life and related topics
68W05 Nonnumerical algorithms
PDF BibTeX XML Cite
Full Text: DOI
References:
[1] Angeline, P. J. Proceedings of the 7thInternational Conference on Evolutionary Programming VII. Evolutionary optimization versus particle swarm optimization: philosophy and performance differences, Vol. 1447, pp.601–610. London: Springer. Lecture Notes in Computer Science
[2] Broomhead D. S., Complex Syst. 2 pp 321– (1988)
[3] DOI: 10.1016/0167-2789(89)90074-2 · Zbl 0671.62099
[4] DOI: 10.1109/72.80341
[5] DOI: 10.1109/4235.985692 · Zbl 05451976
[6] Clerc M., Proceedings of the Congress on Evolutionary Computation pp 1951– (1999)
[7] Haykin S., Neural Networks: A Comprehensive Foundation · Zbl 0828.68103
[8] DOI: 10.1109/TSMCB.2003.818557
[9] Kennedy J., Proceedings of the 2000 Congress on Evolutionary Computation pp 1507–
[10] Kennedy J., Proceedings of the Congress on Evolutionary Computation 3 pp 1931– (1999)
[11] Kennedy, J. and Eberhart, R. C. Proceedings of the IEEE International Conference on Neural Networks IV. Piscataway, NJ. Particle swarm optimization, pp.1942–1948. IEEE Service Center.
[12] Kohonen T. K., Self-organization and Associative Memory (1989) · Zbl 0528.68062
[13] DOI: 10.1016/j.chaos.2006.10.028
[14] DOI: 10.1162/neco.1989.1.2.281
[15] Sanner R. M., IEEE Trans. Neural Netw. 3 pp 837–
[16] Shi Y., Proceedings of Congress on Evolutionary Computation 3 pp 1945– (1999)
[17] Shi Y., Proceedings of 1998 IEEE International Conference on Evolutionary Computation pp 1945–
[18] Suganthan P. N., Proceedings of 1999 Congress on Evolutionary Computation pp 1958–
[19] Sun J., Proceedings of 2004 Congress on Evolutionary Computation pp 325–
[20] Sun, J. and Liu, W. B. Proceedings of 2004 IEEE Conference on Cybernetics and Intelligent Systems. Singapore. A global search strategy of quantum-behaved particle swarm optimization, pp.111–116.
[21] Sun, J. and Liu, W. B. Proceedings of 2005 IEEE International Conference on Systems. Hawaii. Adaptive parameter control for quantum-behaved particle swarm optimization on individual level, pp.3049–3054. Man and Cybernetics.
[22] DOI: 10.1080/00207160601170254 · Zbl 1116.65072
[23] Tou, J. T. and Gonzalez, R. C. 1976.Pattern Recognition Principles, 2, 200–210. Reading, MA: Addison-Wesley.
[24] Van den Bergh F., An analysis of particle swarm optimizers (2001)
[25] Van den Bergh F., Proceedings of 2002 IEEE International Conference on systems pp 96– (2002)
[26] Vesterstrom J., Proceedings of the IEEE 2002 Congress on Evolutionary Computation 2 pp 1570– (2002)
[27] DOI: 10.1109/72.238318
[28] Wang Y., Neurocomputing 70 pp 633– (2007)
[29] Yang X. B., Proceedings of the Fourth International Conference on Machine Learning and Cybernetics pp 4680– (2005)
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. It attempts to reflect the references listed in the original paper as accurately as possible without claiming the completeness or perfect precision of the matching.