Parallel Realisation of the Recurrent Elman Neural Network Learning

  • Jarosław Bilski
  • Jacek Smola̧g
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6114)


The aim of this paper is to present a parallel architecture of Elman Recurrent Network learning algorithm. The solution is based on the high parallel cuboid structure to speed up computation. Parallel neural network structures are explicitly presented and the performance discussion is included.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Bilski, J., Litwiński, S., Smola̧g, J.: Parallel realisation of QR algorithm for neural networks learning. In: Rutkowski, L., Siekmann, J.H., Tadeusiewicz, R., Zadeh, L.A. (eds.) ICAISC 2004. LNCS (LNAI), vol. 3070, pp. 158–165. Springer, Heidelberg (2004)Google Scholar
  2. 2.
    Bilski, J., Smola̧g, J.: Parallel realisation of the RTRN neural network learning. In: Rutkowski, L., Tadeusiewicz, R., Zadeh, L.A., Zurada, J.M. (eds.) ICAISC 2008. LNCS (LNAI), vol. 5097, pp. 11–16. Springer, Heidelberg (2008)CrossRefGoogle Scholar
  3. 3.
    Elman, J.L.: Finding structure in time. Cognitive Science 14, 179–211 (1990)CrossRefGoogle Scholar
  4. 4.
    Kolen, J.F., Kremer, S.C.: A Field Guide to Dynamical Recurrent Neural Networks. IEEE Press, Los Alamitos (2001)Google Scholar
  5. 5.
    Korbicz, J., Patan, K., Obuchowicz, A.: Dynamic neural networks for process modelling in fault detection and isolation. Int. J. Appl. Math. Comput. Sci. 9(3), 519–546 (1999)zbMATHGoogle Scholar
  6. 6.
    Smola̧g, J., Bilski, J.: A systolic array for fast learning of neural networks. In: Proc. of V Conf. Neural Networks and Soft Computing, Zakopane, pp. 754–758 (2000)Google Scholar
  7. 7.
    Smola̧g, J., Rutkowski, L., Bilski, J.: Systolic array for neural networks. In: Proc. of IV Conf. Neural Networks and Their Applications, Zakopane, pp. 487–497 (1999)Google Scholar
  8. 8.
    Williams, R., Zipser, D.: A learning algorithm for continually running fully recurrent neural network. Neural Computation, 270–280 (1989)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2010

Authors and Affiliations

  • Jarosław Bilski
    • 1
  • Jacek Smola̧g
    • 1
  1. 1.Department of Computer EngineeringCzȩstochowa University of TechnologyCzȩstochowaPoland

Personalised recommendations