Abstract
This paper proposes a Gaussian-Cauchy Particle Swarm Optimization (PSO) algorithm to provide the optimized parameters for a Feed Forward Neural Network. The improved PSO trains the Neural Network by optimizing the network weights and bias in the Neural Network. In comparison with the Back Propagation Neural Network, the Gaussian-Cauchy PSO Neural Network converges faster and is immune to local minima.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Cerqueira, J.J.F., Palhares, A.G.B., Madrid, M.K.: A simple adaptive back-propagation algorithm for multilayered feedforward perceptrons. In: Proceedings of the IEEE International Conference on Systems, Man and Cybernetics, vol. 3, p. 6, 6–9 October 2002
Gudise, V.G., Venaayagamoorthy, G.K.: Comparison of particle swarm optimization and back propagation as training algorithms for neural networks. In: Proceedings of the IEEE Swarm Intelligence Symposium (SIS 2003), pp. 110–117 (2003)
Wang, W., Cao, J., et al.: Reservoir parameter prediction of neural network based on particle swarm optimization. J. Southwest Pet. Univ. 29(6), 31 (2007)
Juang, C.F.: A hybrid genetic algorithm and particle swarm optimization for recurrent network design. IEEE Trans. Syst. Man Cybern. 32, 997–1006 (2004)
Settles, M., Raylander, B.: Neural network learning using particle swarm optimizers. In: Advances in Information Science and Soft Computing, pp. 224–226 (2002)
Eberhart, R.C., Shi, Y.: Comparison between genetic algorithms and particle swarm optimization. In: Proceedings of the 7th Annual Conference on Genetic and Evolutionary Computation, pp. 611–616. Springer, Berlin (1998)
Zhang, J.-R., et al.: A hybrid particle swarm optimization-back propagation algorithm for feed forward neural network training. Appl. Math. Comput. 185, 1026–1037 (2007)
George, M., Tsang, W.W.: The Ziggurat method for generating random variables. J. Stat. Softw. 5(8), 1–7 (2000)
Acknowledgments
This work was supported by Petronas Corporation, Petroleum Research Fund (PRF) No. 0153AB-A33.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer International Publishing AG
About this paper
Cite this paper
Melo, H., Zhang, H., Vasant, P., Watada, J. (2018). Training Method for a Feed Forward Neural Network Based on Meta-heuristics. In: Pan, JS., Tsai, PW., Watada, J., Jain, L. (eds) Advances in Intelligent Information Hiding and Multimedia Signal Processing. IIH-MSP 2017. Smart Innovation, Systems and Technologies, vol 82. Springer, Cham. https://doi.org/10.1007/978-3-319-63859-1_46
Download citation
DOI: https://doi.org/10.1007/978-3-319-63859-1_46
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-63858-4
Online ISBN: 978-3-319-63859-1
eBook Packages: EngineeringEngineering (R0)