MULTIDIMENSIONAL POLYNOMIAL POWERS OF SIGMOID (PPS) WAVELET NEURAL NETWORKS

João Fernando Marar, Helder Coelho

2008

Abstract

Wavelet functions have been used as the activation function in feedforward neural networks. An abundance of R&D has been produced on wavelet neural network area. Some successful algorithms and applications in wavelet neural network have been developed and reported in the literature. However, most of the aforementioned reports impose many restrictions in the classical backpropagation algorithm, such as low dimensionality, tensor product of wavelets, parameters initialization, and, in general, the output is one dimensional, etc. In order to remove some of these restrictions, a family of polynomial wavelets generated from powers of sigmoid functions is presented. We described how a multidimensional wavelet neural networks based on these functions can be constructed, trained and applied in pattern recognition tasks. As an example of application for the method proposed, it is studied the exclusive-or (XOR) problem.

References

  1. Avci, E. (2007). An expert system based on wavelet neural network-adaptive norm entropy for scale invariant texture classification. Expert Systems with Applications, 32:919-926.
  2. Chen, H. and Hewit, J. (2000). Application of wavelet transform and neural networks to recognition and classivication of blemishes. Mechatronics, 10:699-711.
  3. Chen, Y., Yang, B., and Dong, J. (2006). Time series prediction using a local linear wavelet neural network. Neurocomputing, (69):449-465.
  4. Chui, C. (1992). An Introduction to Wavelets. Academic Press.
  5. Cybenko, G. (1989). Approximation by superposition of a sigmoidal function. Mathematics of Control, signals and Systems, 3:303-314.
  6. Daubechies, I. (1992). Ten lecture on wavelets. Society for Industrial and Applied Mathematics (SIAM).
  7. de Queiroz, R. A. B. and Marar, J. F. (2007). Algorítmos heurísticos para a selec¸a˜o de neuroˆnios em redes neurais polinomios poteˆncias de sigmoide (pps)-wavelet. TEMA Tend. Mat. Apl. Comput., 8(1):129-138.
  8. Fan, J. and Wang, X. F. (2005). A wavelet view of smallworld networks. IEEE Transactions on Circuits and Systems, pages 1-4.
  9. Funahashi, K. (1989). On the approximate realization of continuos mappings by neural networks. Neural Networks, (2):183-192.
  10. Hecht-Nilsen, R. (1987). Kolmogorov's mapping neural networks existence theorem. In 1st IEEE Inter. Conf. on Neural Networks, volume 3, pages 11-14.
  11. Jiang, X., Mahadevan1, S., and Adeli, H. (2007). Bayesian wavelet packet denoising for structural system identification. Struct. Control Health Monit., 14:333-356.
  12. Marar, J. F. (1997). Polinomios Poteˆncias de Sigmoide (PPS): Uma nova Técnica para Aproximac¸a˜o de Func¸ o˜es, Construc¸ a˜o de Wavenets e suas aplicac¸ o˜es em Processamento de Imagens e Sinais. PhD thesis, Universidade Federal de Pernambuco - Departamento de Informática.
  13. Misra, B. B., Dash, P. K., and Panda, G. (2007). Pattern classification using local linear wavelet neural network. International Conference on Information and Communication Technology, pages 92-95.
  14. Oussar, Y. and Dreyfus, G. (2000). Initialization by selection for wavelet neural traing. Neurocomputing, 34:131-143.
  15. Pati, Y. and Krishnaprasad, P. (1993). Analysis and synthesis of feedforward neural networks using discrete affine wavelet transformations. IEEE Transactions on Neural Networks, 4(1):73-85.
  16. Zhang, H. and Pu, J. (2006). A novel self-adaptive control framework via wavelet neural netwok. In 6th World congress on intelligent control and automation, pages 2254-2258.
  17. Zhang, Q. and Benveniste, A. (1992). Wavelet networks. IEEE Transactions on Neural Networks, 3(6):889- 898.
  18. Zhang, Z. and San, Y. (2004). Adaptive wavelet neural network for prediction of hourly nox and no2 concentrations. In Winter Simulation Conference, pages 1770- 1778.
Download


Paper Citation


in Harvard Style

Fernando Marar J. and Coelho H. (2008). MULTIDIMENSIONAL POLYNOMIAL POWERS OF SIGMOID (PPS) WAVELET NEURAL NETWORKS . In Proceedings of the First International Conference on Bio-inspired Systems and Signal Processing - Volume 2: BIOSIGNALS, (BIOSTEC 2008) ISBN 978-989-8111-18-0, pages 261-268. DOI: 10.5220/0001067302610268


in Bibtex Style

@conference{biosignals08,
author={João Fernando Marar and Helder Coelho},
title={MULTIDIMENSIONAL POLYNOMIAL POWERS OF SIGMOID (PPS) WAVELET NEURAL NETWORKS},
booktitle={Proceedings of the First International Conference on Bio-inspired Systems and Signal Processing - Volume 2: BIOSIGNALS, (BIOSTEC 2008)},
year={2008},
pages={261-268},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0001067302610268},
isbn={978-989-8111-18-0},
}


in EndNote Style

TY - CONF
JO - Proceedings of the First International Conference on Bio-inspired Systems and Signal Processing - Volume 2: BIOSIGNALS, (BIOSTEC 2008)
TI - MULTIDIMENSIONAL POLYNOMIAL POWERS OF SIGMOID (PPS) WAVELET NEURAL NETWORKS
SN - 978-989-8111-18-0
AU - Fernando Marar J.
AU - Coelho H.
PY - 2008
SP - 261
EP - 268
DO - 10.5220/0001067302610268