Full-text resources of PSJD and other databases are now available in the new Library of Science.
Visit https://bibliotekanauki.pl

PL EN


Preferences help
enabled [disable] Abstract
Number of results
2013 | 124 | 3 | 554-557

Article title

Neural Approximation of Empirical Functions

Authors

Content

Title variants

Languages of publication

EN

Abstracts

EN
The paper presents the results of simulation studies of selected neural network structures used for non-linear function approximation based on a limited accuracy data. There was performed the analysis of the interdependence of the network structure and the size of the set of learning patterns. The approximation inaccuracy was expressed by the uncertainty interval width. The approximation properties of the neural method were compared with those of the piece-wise linear and polynomial: "cubic" and "spline" methods.

Keywords

Contributors

author
  • Institute of Measurement Science, Electronics and Control at the Silesian University of Technology Akademicka 10, 44-100 Gliwice, Poland

References

  • [1] S. Haykin, Neural Networks: A Comprehensive Foundation, 3rd ed., Prentice Hall, London 2008
  • [2] M. Gupta, N. Homma, L. Jin, Static and Dynamic Neural Networks: From Fundamentals to Advanced Theory, Wiley, New Jersey 2003
  • [3] X. He, S. Xu, Process Neural Networks, Springer-Verlag, Berlin 2009
  • [4] A.R. Barron, IEEE Trans. Inf. Theory 36, 930 (1993)
  • [5] K. Hornik, Neural Networks 2, 251 (1991)
  • [6] T. Chen, H. Chen, IEEE Trans. Neural Networks 4, 904 (1995)
  • [7] K. Hornik, M. Stinchcombe, H. White, Neural Networks 2, 359 (1989)
  • [8] J. Park, I.W. Sandberg, Neural Comput. 2, 246 (1991)
  • [9] S. Ablameyko, L. Goras, M. Goris, V. Piuri, Neural Networks for Instrumentation, Measurement and Related Industrial Applications, IOS Press, Oxford 2003
  • [10] W. Jakubik, M. Urbanczyk, E. Maciak, T. Pustelny, Bull. Pol. Acad. Sci., Techn. Sci. 56, 133 (2008)
  • [11] J. Ignac-Nowicka, T. Pustelny, Z. Opilski, E. Maciak, W. Jakubik, M. Urbanczyk, Opt. Eng. 42, 2978 (2003)
  • [12] T. Pustelny, J. Ignac-Nowicka, B. Jarząbek, A. Burian, Opt. Appl. 34, 551 (2004)
  • [13] A.P. Singh, T.S. Kamal, S. Kumar, ISA Trans. 3, 319 (2006)
  • [14] P. Kluk, R.Z. Morawski, in: Proc. IEEE Instrum. Meas. Technol. Conf. - IMTC'96, Brussels (Belgium), 1996, p. 581
  • [15] V. Vapnik, The Nature of Statistical Learning Theory. Information Science and Statistics, Springer-Verlag, New York 2000
  • [16] D. Hush, B. Horne, IEEE Sign. Proc. Mag. 8, (1993)
  • [17] S.J. Khavinson, Math. Notes 4, 406 (1994)
  • [18] V. Kurkova, Neural Networks 5, 501 (1992)
  • [19] B.A. Smith, R.W. McClendon, G. Hoogenboom, Int. J. Comput. Intellig. 3, 179 (2006)
  • [20] A. Rabiatul, A. Zainal, IIUM Eng. J., Spec. Iss. Sci. Ethics 6, 45 (2011)
  • [21] S. Olyaee, S. Hamedi, J. Phys., Conf. Series 276, 1 (2011)
  • [22] G.-B. Huang, Q.-Y. Zhu, Ch.-K. Siew, IEEE Trans. Neural Networks 4, 863 (2006)
  • [23] J. Jakubiec, P. Makowski, J. Roj, IEEE Trans. Instrum. Measur. 3, 649 (2009)
  • [24] J. Roj, Przegląd Elektrotechniczny 1a, 84 (2013) (in Polish)
  • [25] C. de Boor, A Practical Guide to Splines, Springer-Verlag, New York 2001

Document Type

Publication order reference

Identifiers

YADDA identifier

bwmeta1.element.bwnjournal-article-appv124n345kz
JavaScript is turned off in your web browser. Turn it on to take full advantage of this site, then refresh the page.