Abstract
In this paper, an improved approach which combines random particle swarm optimization with BP is proposed to obtain better generalization performance and faster convergence rate. It is well known that the backpropagation (BP) algorithm has good local search ability but it is easily trapped to local minima. On the contrary, the particle swarm optimization algorithm (PSO), with good global search ability, converges rapidly during the initial stages of a global research. Since the PSO suffers from the disadvantage of losing diversity, it converges more slow around the global minima. Hence, the global search is combined with local search reasonably in the improved approach which is called as RPSO-BP. Moreover, in order to improve the diversity of the swarm in the PSO, a random PSO (RPSO) is proposed in the paper. Compared with the traditional learning algorithms, the improved learning algorithm has much better convergence accuracy and rate. Finally, the experimental results are given to verify the efficiency and effectiveness of the proposed algorithm.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Homik, K.: Mulitilayer feedforward networks are universal approximators. Neural Networks 2, 359–366 (1989)
Chen, D.S., Jain, R.C.: A robust Back-propagation Algorithm for Function Approximation. IEEE Trans. on Neural Network 5, 467–479 (1994)
Meng, J.L., Sun, Z.Y.: Application of combined neural networks in nonlinear function approximation. In: Proceedings of the Third World Congress on Intelligent Control and Automation, Hefei, pp. 839–841 (2000)
Kennedy, J., Eberhart, R.: Particle Swarm Optimization. In: IEEE International Conference on Neural Networks, Perth, IEEE Service Cente, Piscataway, NJ, pp. 1942–1948 (1995)
Li, X.P., Zhang, H.Y.: Improvement of Simulated Annealing Algorithm. Software Guide 7(4), 47–48 (2000)
Angeline, P.J., Sauders, G.M., Pollack, J.B.: An evolutionary algorithm that constructs recurrent neural networks. IEEE Trans. Neural Networks 5(1), 54–65 (1994)
Yao, X.: A review of evolutionary artifical neural networks. Int. J. Intell. Syst. 8(4), 539–567 (1993)
Han, F., Ling, Q.H., Huang, D.S.: Modified Constrained Learning Algorithms Incorporating Additional Functional Constraints Into Neural Networks. Information Sciences 178(3), 907–919 (2008)
Wang, X.G., Tang, Z., Tamura, H., Ishii, M.: A modified error function for the backpropagation algorithm. Neurocomputing 57, 477–484 (2004)
Liu, Y.H., Chen, R., Peng, W., Zhou, L.: Optimal Design for Learning Rate of BP Neutral Network. Journal of Hubei University of Technology 22(2), 1–3 (2007)
Ma, Y.Q., Huo, Z.Y., Yang, Z.: The Implementation of the Improved BP Algorithm by Adding the Item of the Momentum. Sci-Tech Information Development & Economy 16(8), 157–158 (2006)
Zhang, J.-R., Zhang, J., Lok, T.-M., Lyu, M.R.: A hybrid particle swarm optimization-back-propagation algorithm for feedforward neural network training. Applied Mathematics and Computation 185(2), 1026–1037 (2007)
Guo, W., Qiao, Y.Z., Hou, H.Y.: BP neural network optimized with PSO algorithm and its application in forecasting. In: Proc. 2006 IEEE International Conference on Information Acquisition, Weihai, Shandong,China, August 2006, pp. 617–621 (2006)
Han, F., Ling, Q.H.: A New Approach for Function Approximation Incorporating Adaptive Particle Swarm Optimization And A Priori Information. Applied Mathematics and Computation 205(2), 792–798 (2008)
Shi, Y.H., Eberhat, R.C.: Parameter selection in particle swarm optimization. In: Proc. of 1998 Annual conference on Evolutionary Programming, San Diego, pp. 591–600 (1998)
Shi, Y.H., Eberhat, R.C.: A modified particle swarm optimizer. In: Proc.of IEEE World Conf. on Computation Intelligence, pp. 69–73 (1998)
Clerc, M., Kennedy, J.: The particle swarm:explosion,stability,and convergence in a multi-dimensional complex space. IEEE Trans. Evolut. Comput. 6(1), 58–73 (2002)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2009 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Cui, Y., Ju, SG., Han, F., Gu, TY. (2009). An Improved Approach Combining Random PSO with BP for Feedforward Neural Networks. In: Deng, H., Wang, L., Wang, F.L., Lei, J. (eds) Artificial Intelligence and Computational Intelligence. AICI 2009. Lecture Notes in Computer Science(), vol 5855. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-05253-8_40
Download citation
DOI: https://doi.org/10.1007/978-3-642-05253-8_40
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-05252-1
Online ISBN: 978-3-642-05253-8
eBook Packages: Computer ScienceComputer Science (R0)