The Problem of Organizing and Partitioning Large Data Sets in Learning Algorithms for SOM-RBF Mixed Structures - Application to the Approximation of Environmental Variables

José A. Torres, Sergio Martinez, Francisco J. Martinez, Mercedes Peralta

2013

Abstract

The paper presents a technique to partition and sort data in a large training set for building models of envi-ronmental function approximation using RBFs networks. This process allows us to make very accurate ap-proximations of the functions in a time fraction related to the RBF networks classic training proccess. Fur-thermore, this technique avoids problems of buffer overflow in the training algorithm execution. The results obtained proved similar accuracy to those obtained with a classical model in a time substantially less, opening, on the other hand, the way to the parallelization process using GPUs technology.

References

  1. Jacobs, R. J.; “A competitive modular connectionist architecture,” Advances in Neural Information Processing Systems, vol. 3, pp. 767-773, 1991.
  2. de Felipe, J.; “Microcircuits in the brain,” in Proceeding of the IWANN'97, pp. 1-14. 1997,
  3. Arriaza, José A. Torres, Francisco Guindos Rojas, Mercedes Peralta Lopez, Manuel Cantón “An automatic cloud-masking system using backpro neural nets for avhrr scenes,” IEEE Transactions on Geoscience and Remote Sensing, vol. 41, no 4, pp. 826-831, 2003.
  4. Rao, K. V. G.; “Soft computing-neural networks ensembles,” Journal of Theoretical and Applied Information Technology,pp. 45-50, 2005.
  5. Broomhead, D. L.; “Multivariable functional interpolation and adaptive networks,” Complex Systems, vol. 2, pp. 321-355, 1988.
  6. Poggio, T.; “Networks for approximation and learning,” IEEE, vol. 78, pp. 1481-1497, 1990.
  7. Haykin, S.; “Neural networks, a comprehensive foundations,” IEEE press, 1994.
  8. Brassard, P.; Fundamentals of algoritmics. Prentice Hall, 1995.
  9. Aho, A. V., J. E. Hopcroft, J. D. Ullman, Estructuras de datos en Java. Addison-Wesley, 2000/2004.
  10. Kohonen, T.; Self-Organizing Maps. Springer, 1990.
  11. Sedgewick, R.; Algorithms. Addison-Wesley, 2002.
  12. Cruz, M., M. Espínola, R. Ayala, M. Peralta, José A.Torres, “How Can Neural Networks Speed Up Ecological Regionalization Friendly?. ICCN 2010. International Conference on Neural Computation. Part of 2th. International Joint Conference on Computational Intelligence. INSTICC. 2010.
Download


Paper Citation


in Harvard Style

Torres J., Martinez S., Martinez F. and Peralta M. (2013). The Problem of Organizing and Partitioning Large Data Sets in Learning Algorithms for SOM-RBF Mixed Structures - Application to the Approximation of Environmental Variables . In Proceedings of the 5th International Joint Conference on Computational Intelligence - Volume 1: NCTA, (IJCCI 2013) ISBN 978-989-8565-77-8, pages 497-501. DOI: 10.5220/0004554604970501


in Bibtex Style

@conference{ncta13,
author={José A. Torres and Sergio Martinez and Francisco J. Martinez and Mercedes Peralta},
title={The Problem of Organizing and Partitioning Large Data Sets in Learning Algorithms for SOM-RBF Mixed Structures - Application to the Approximation of Environmental Variables},
booktitle={Proceedings of the 5th International Joint Conference on Computational Intelligence - Volume 1: NCTA, (IJCCI 2013)},
year={2013},
pages={497-501},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0004554604970501},
isbn={978-989-8565-77-8},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 5th International Joint Conference on Computational Intelligence - Volume 1: NCTA, (IJCCI 2013)
TI - The Problem of Organizing and Partitioning Large Data Sets in Learning Algorithms for SOM-RBF Mixed Structures - Application to the Approximation of Environmental Variables
SN - 978-989-8565-77-8
AU - Torres J.
AU - Martinez S.
AU - Martinez F.
AU - Peralta M.
PY - 2013
SP - 497
EP - 501
DO - 10.5220/0004554604970501