Abstract
This paper proposes a new learning method for process neural networks (PNNs) based on the Gaussian mixture functions and particle swarm optimization (PSO), called PSO-LM. First, the weight functions of the PNNs are specified as the generalized Gaussian mixture functions (GGMFs). Second, a PSO algorithm is used to optimize the parameters, such as the order of GGMFs, the number of hidden neurons, the coefficients, means and variances of Gaussian functions and the thresholds in PNNs. In PSO-LM, the parameter space is transformed from the function space to real number space by using GGMFs. PSO can give a global search in the real number parameter space by avoiding the premature and gradient calculations in back propagation method. According to our analysis and several experiments, PSO-LM can outperform current basis function expansion based learning method (BFE-LM) for PNNs and the classic back propagation neural networks (BPNNs).
Access provided by Autonomous University of Puebla. Download to read the full chapter text
Chapter PDF
Similar content being viewed by others
References
He, X.G., Xu, S.H.: Process Neural Networks. Science Press, Beijing (2007)
He, S., Hu, C., Song, G.J., Xie, K.Q., Sun, Y.Z.: Real-Time Short-Term Traffic Flow Forecasting Based on Process Neural Network. In: Sun, F., Zhang, J., Tan, Y., Cao, J., Yu, W. (eds.) ISNN 2008, Part II. LNCS, vol. 5264, pp. 560–569. Springer, Heidelberg (2008)
Wu, T.S., Xie, K.Q., Song, G.J., He, X.G.: Numerical Learning Method for Process Neural Network. In: Yu, W., He, H., Zhang, N. (eds.) ISNN 2009. LNCS, vol. 5551, pp. 670–678. Springer, Heidelberg (2009)
Kennedy, J., Eberhart, R.C.: Particle Swarm Optimization. In: Proc. of the IEEE International Conference on Neural Networks 1995, pp. 1942–1948 (1995)
Van Den Bergh, F., Engelbrecht, A.P.: Training Product Unit Networks Using Cooperative Particle Swarm Optimization. In: Proc. of the IEEE International Joint Conference on Neural Networks 2001, vol. 1, pp. 126–131 (2001)
Bratton, D., Kennedy, J.: Defining a Standard for Particle Swarm Optimization. In: Proc. of the IEEE Swarm Intelligence Symposlum (SIS), pp. 120–127 (2007)
Yuan, L.H., Li, Z., Song, J.S.: Probabillty Density Function Approximation Using Gaussian Mixture Model. Radio Communications Technology 33(2), 20–22 (2007)
Freeway Performance Measurement System (PeMS), http://pems.eecs.berkeley.edu
Asuncion, A., Newman, D.J.: UCI Machine Learning Repository. In: School of Information and Computer Science. University of California, Irvine (2007), http://archive.ics.uci.edu/ml/datasets/Spambase
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2010 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Liu, K., Tan, Y., He, X. (2010). Particle Swarm Optimization Based Learning Method for Process Neural Networks. In: Zhang, L., Lu, BL., Kwok, J. (eds) Advances in Neural Networks - ISNN 2010. ISNN 2010. Lecture Notes in Computer Science, vol 6063. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-13278-0_36
Download citation
DOI: https://doi.org/10.1007/978-3-642-13278-0_36
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-13277-3
Online ISBN: 978-3-642-13278-0
eBook Packages: Computer ScienceComputer Science (R0)