Robust Recursive Complex Extreme Learning Machine Algorithm for Finite Numerical Precision

  • Junseok Lim
  • Koeng Mo Sung
  • Joonil Song
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3971)


Recently, a new learning algorithm for single-hidden-layer feedforward neural network (SLFN) named the complex extreme learning machine (C-ELM) has been proposed in [1]. In this paper, we propose a numerically robust recursive least square type C-ELM algorithm. The proposed algorithm improves the performance of C-ELM especially in finite numerical precision. The computer simulation results in the various precision cases show the proposed algorithm improves the numerical robustness of C-ELM.


Hide Neuron Feedforward Neural Network Radial Basis Function Network Input Weight Hide Layer Output Matrix 
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.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Huang, M., Saratchandran, P., Sundararajan, N.: Fully Complex Extreme Learning Machine. Neurocomputing 68, 306–314 (2005)CrossRefGoogle Scholar
  2. 2.
    Haykin, S.: Adaptive Filter Theory, 3rd edn. Prentice-Hall, Upper Saddle River (1996)Google Scholar
  3. 3.
    Douglas, S.C.: Numerically - Robust. O(N2) Recursive Least-Squares Estimation Using Least Squares Prewhitening. In: Proceeding of International Conference of Acoustics, Speech, and Signal Processing (ICASSP 2000), vol. 1, pp. 412–415 (2000)Google Scholar
  4. 4.
    Dasilva, F.M., Almeida, L.B.: A Distributed Decorrelation Algorithm. In: Gelenbe, E. (ed.) Neural Networks: Advances and Applications, pp. 145–163. Elsevier Science, Amsterdam (1991)Google Scholar
  5. 5.
    Douglas, S.C., Cichocki, A.: Neural Networks for Blind Decorrelation of Signals. IEEE Trans. Signal Processing 45, 2829–2842 (1997)CrossRefGoogle Scholar
  6. 6.
    Cha, I., Kassam, S.A.: Channel Equalization Using Adaptive Complex Radial Basis Function Networks. IEEE J. Sel. Area. Comm. 13, 122–131 (1995)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Junseok Lim
    • 1
  • Koeng Mo Sung
    • 2
  • Joonil Song
    • 3
  1. 1.Dept. of Electronics EngineeringSejong UniversitySeoulKorea
  2. 2.School of Electrical EngineeringSeoul National UniversitySeoulKorea
  3. 3.Samsung Electronics Co., Ltd 

Personalised recommendations