COMBINATION OF BREEDING SWARM OPTIMIZATION AND BACKPROPAGATION ALGORITHM FOR TRAINING RECURRENT FUZZY NEURAL NETWORK

Soheil Bahrampour, Sahand Ghorbanpour, Amin Ramezani

Abstract

The usage of recurrent fuzzy neural network has been increased recently. These networks can approximate the behaviour of the dynamical systems because of their feedback structure. The Backpropagation of error has usually been used for training this network. In this paper, a novel approach for learning the parameters of RFNN is proposed using combination of the backpropagation and breeding particle swarm optimization. A comparison of this approach with previous methods is also made to demonstrate the effectiveness of this algorithm. Particle swarm is a derivative free, globally optimizing approach that makes the training of the network easier. These can solve the problems of gradient based method, which are instability, local minima and complexity of differentiating.

References

  1. Angeline, P., Saunders, G., Pollack, J.,1994. An evolutionary algorithm that constructs recurrent neural networks.
  2. Engelbrecht, A. P., 2002. Computational Intelligence. John Wiley and Sons,2002.
  3. Kennedy, J., Eberhart, R., 1995. Particle Swarm Optimization. IEEE International Conference on Neural Networks , pp. 1942-1948.
  4. Ku, C. C., Lee, K. Y., 1995. Diagonal recurrent neural networks for dynamic systems control. IEEE Trans. Neural Networks, vol. 6, pp. 144-156.
  5. Lee, C. H., Teng, C., 2000. Identification and Control of Dynamic Systems Using Recurrent Fuzzy Neural Networks. In IEEE Transactions on fuzzy systems, vol.8, NO. 4, 349,366 .
  6. Settles, M., Nathan, P., Soule, T, 2005. Breeding Swarms: A New Approach to Recurrent Neural Network Training. GECCO'05, June 25-29 Washington, DC, USA.
  7. Soule, T., Chen, Y., Wells, R.,2002. . Evolving a strongly recurrent neural network to simulate biological eurons. In the proceedings of The 28th Annual Conference of the IEEE Industrial Electronics Society.
  8. Surmann, H., Maniadakis, M., 2001. Learning feedforward and recurrent fuzzy systems: A genetic approach. Journal of System Architecture 47, 649-662.
  9. Williams, R. J., Zipser, D.,1989. A learning algorithm for continually running fully recurrent neural networks. Neural Computation., vol. 1, pp. 270-280.
Download


Paper Citation


in Harvard Style

Bahrampour S., Ghorbanpour S. and Ramezani A. (2008). COMBINATION OF BREEDING SWARM OPTIMIZATION AND BACKPROPAGATION ALGORITHM FOR TRAINING RECURRENT FUZZY NEURAL NETWORK . In Proceedings of the Fifth International Conference on Informatics in Control, Automation and Robotics - Volume 1: ICINCO, ISBN 978-989-8111-30-2, pages 314-317. DOI: 10.5220/0001491703140317


in Bibtex Style

@conference{icinco08,
author={Soheil Bahrampour and Sahand Ghorbanpour and Amin Ramezani},
title={COMBINATION OF BREEDING SWARM OPTIMIZATION AND BACKPROPAGATION ALGORITHM FOR TRAINING RECURRENT FUZZY NEURAL NETWORK},
booktitle={Proceedings of the Fifth International Conference on Informatics in Control, Automation and Robotics - Volume 1: ICINCO,},
year={2008},
pages={314-317},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0001491703140317},
isbn={978-989-8111-30-2},
}


in EndNote Style

TY - CONF
JO - Proceedings of the Fifth International Conference on Informatics in Control, Automation and Robotics - Volume 1: ICINCO,
TI - COMBINATION OF BREEDING SWARM OPTIMIZATION AND BACKPROPAGATION ALGORITHM FOR TRAINING RECURRENT FUZZY NEURAL NETWORK
SN - 978-989-8111-30-2
AU - Bahrampour S.
AU - Ghorbanpour S.
AU - Ramezani A.
PY - 2008
SP - 314
EP - 317
DO - 10.5220/0001491703140317