Several Enhancements to Hermite-Based Approximation of One-Variable Functions (original) (raw)

Abstract

Several enhancements and comments to Hermite-based one-variable function approximation are presented. First of all we prove that a constant bias extracted from the function contributes to the error decrease. We demonstrate how to choose that bias. Secondly we show how to select a basis among orthonormal functions to achieve minimum error for a fixed dimension of an approximation space. Thirdly we prove that loss of orthonormality due to truncation of the argument range of the basis functions does not effect the overall error of approximation and the expansion coefficients. We show how this feature can be used. An application of the obtained results to ECG data compression is presented.

Preview

Unable to display preview. Download preview PDF.

Similar content being viewed by others

References

  1. Beliczynski, B.: Properties of the Hermite activation functions in a neural approximation scheme. In: Beliczynski, B., Dzielinski, A., Iwanowski, M., Ribeiro, B. (eds.) ICANNGA 2007. LNCS, vol. 4432, pp. 46–54. Springer, Heidelberg (2007)
    Chapter Google Scholar
  2. Linh, T.H.: Modern Generations of Artificial Neural Networks and their Applications in Selected Classification Problems. Publishing House of the Warsaw University of Technology (2004)
    Google Scholar
  3. Ma, L., Khorasani, K.: Constructive feedforward neural networks using Hermite polynomial activation functions. IEEE Transactions on Neural Networks 16, 821–833 (2005)
    Article Google Scholar
  4. Kwok, T., Yeung, D.: Constructive algorithms for structure learning in feedforward neural networks for regression problems. IEEE Trans. Neural Netw. 8(3), 630–645 (1997)
    Article Google Scholar
  5. Kwok, T., Yeung, D.: Objective functions for training new hidden units in constructive neural networks. IEEE Trans. Neural Networks 8(5), 1131–1148 (1997)
    Article Google Scholar
  6. Kreyszig, E.: Introductory functional analysis with applications. J. Wiley, Chichester (1978)
    MATH Google Scholar

Download references

Author information

Authors and Affiliations

  1. Institute of Control and Industrial Electronics, Warsaw University of Technology, ul. Koszykowa 75, 00-662, Warszawa, Poland
    Bartlomiej Beliczynski
  2. Department of Informatics Engineering, Center for Informatics and Systems, University of Coimbra, Polo II, P-3030-290, Coimbra, Portugal
    Bernardete Ribeiro

Authors

  1. Bartlomiej Beliczynski
  2. Bernardete Ribeiro

Editor information

Véra Kůrková Roman Neruda Jan Koutník

Rights and permissions

© 2008 Springer-Verlag Berlin Heidelberg

About this paper

Cite this paper

Beliczynski, B., Ribeiro, B. (2008). Several Enhancements to Hermite-Based Approximation of One-Variable Functions. In: Kůrková, V., Neruda, R., Koutník, J. (eds) Artificial Neural Networks - ICANN 2008. ICANN 2008. Lecture Notes in Computer Science, vol 5163. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-87536-9\_2

Download citation

Keywords

These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Publish with us