TRAINING RADIAL BASIS FUNCTION NETWORKS BY GENETIC ALGORITHMS

Juliano F. da Mota, Paulo H. Siqueira, Luzia V. de Souza, Adriano Vitor

Abstract

One of the issues of modeling a RBFNN - Radial Basis Function Neural Network consists of determining the weights of the output layer, usually represented by a rectangular matrix. The inconvenient characteristic at this stage it’s the calculation of the pseudo-inverse of the activation values matrix. This operation may become computationally expensive and cause rounding errors when the amount of variables is large or the activation values form an ill-conditioned matrix so that the model can misclassify the patterns. In our research, Genetic Algorithms for continuous variables determines the weights of the output layer of a RBNN and we’ve made a comparsion with the traditional method of pseudo-inversion. The proposed approach generates matrices of random normally distributed weights which are individuals of the population and applies the Michalewicz’s genetic operators until some stopping criteria is reached. We’ve tested four classification patterns databases and an overall mean accuracy lies in the range 91–98%, in the best case and 58–63%, in the worse case.

References

  1. Changbing, L. and Wei, H. (2010). Application of genetic algorithm-rbf neural network in water environment risk prediction. 2nd International Conference on Computer Engineering and Technology 2010, pages 239-242.
  2. Frank, A. and Asuncion, A. (2010). UCI machine learning repository.
  3. Haykin, S. (2001). Redes neurais - princípios e práticas. Bookman.
  4. Holland, J. (1975). Adaption in Natural and Artificial Systems. MIT Press.
  5. Kurban, T. and Bes¸dok, E. (2009). A comparsion of rbf neural netowrk training algorithms for inertial sensor based terrian classification. Sensors, pages 6312- 6329.
  6. Li, N. and Ling, H. (2011). Study of an algorithm of garbf neural network generalized predictive control for generating unit. International Conference on Electric Information and Control Engineering 2011, pages 1723-1726.
  7. Man, K., Tang, K., and Kwong, S. (1996). Genetic algorithms: concepts and applications. IEEE Transactions on Industrial Electronics, 43(5):519-534.
  8. Michalewicz, Z., Logan, T. D., and Swaminathan, S. (1994). Evolutionary operators for continuous convex parameter spaces. Proceedings of the 3rd Annual Conference on Evolutionary Programming, pages 84- 97.
  9. Ming, Z. Y., Bin, Z. Y., and Zhong, L. L. (2010). Application of genetic algorithm and rbf neural network in network flow prediction. 3rd IEEE International Conference on Computer Science and Information Technology 2010, pages 298-301.
  10. Silva, I. N., Spatti, D. H., and Flauzino, R. A. (2010). Redes neurais artificiais - para engenharia e ciências aplicadas. Artliber.
  11. Siqueira, P., Scheer, S., and Steiner, M. T. A. (2005). Application of the "winner takes all" principle in wang's recurrent neural network for the assignment problem. Lecture Notes in Computer Science, 3496(1):731- 738.
Download


Paper Citation


in Harvard Style

F. da Mota J., H. Siqueira P., V. de Souza L. and Vitor A. (2012). TRAINING RADIAL BASIS FUNCTION NETWORKS BY GENETIC ALGORITHMS . In Proceedings of the 4th International Conference on Agents and Artificial Intelligence - Volume 1: ICAART, ISBN 978-989-8425-95-9, pages 373-379. DOI: 10.5220/0003751903730379


in Bibtex Style

@conference{icaart12,
author={Juliano F. da Mota and Paulo H. Siqueira and Luzia V. de Souza and Adriano Vitor},
title={TRAINING RADIAL BASIS FUNCTION NETWORKS BY GENETIC ALGORITHMS},
booktitle={Proceedings of the 4th International Conference on Agents and Artificial Intelligence - Volume 1: ICAART,},
year={2012},
pages={373-379},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0003751903730379},
isbn={978-989-8425-95-9},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 4th International Conference on Agents and Artificial Intelligence - Volume 1: ICAART,
TI - TRAINING RADIAL BASIS FUNCTION NETWORKS BY GENETIC ALGORITHMS
SN - 978-989-8425-95-9
AU - F. da Mota J.
AU - H. Siqueira P.
AU - V. de Souza L.
AU - Vitor A.
PY - 2012
SP - 373
EP - 379
DO - 10.5220/0003751903730379