On Stability of Oja Algorithm

  • Radosław Sikora
  • Władysław Skarbek
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1424)


By elementary tools of matrix analysis, we show that the discrete dynamical system defined by Oja algorithm is stable in the ball K(0,81/64) if only gains β n are bounded by (2B)−1, where B = b 2 and b is the bound for the learning sequence. We also define a general class of Oja’s systems (with gains satisfying stochastic convergence conditions) which tend to the infinity with exponential rate if only their initial states are chosen too far from the zero point.


Learning Sequence Stochastic Approximation Discrete Dynamical System Principal Vector Digit Recognition 
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.
    Diamantaras, K.I., Kung, S.Y. (1995) Principal component neural networks — Theory and applications, John Wiley & Sons, Inc.Google Scholar
  2. 2.
    Duflo, M. (1997) Random iterative models, Appl. Math., 34 Springer.Google Scholar
  3. 3.
    Karhunen, J. (1994) Stability of Oja’s PCA subspace rule, Neural Computation.Google Scholar
  4. 4.
    Kushner, H.J., Clark, D.S. (1978) Stochastic approximation for constrained and unconstrained systems, Appl. Math. Sci., 26. Springer.Google Scholar
  5. 5.
    Kushner, H.J., Yin, G. (1997) Stochastic approximation and applications, Springer.Google Scholar
  6. 6.
    Oja, E. (1982) A simplified neuron model as a principal component analyzer, J. Math. Biology, 15, 267–273.zbMATHCrossRefMathSciNetGoogle Scholar
  7. 7.
    Skarbek, W., Ignasiak, K. (1997) Handwritten digit recognition by local principal components analysis, ISMIS’97, International Symposium for Methodology of Intelligent Systems, 217–226, Charlotte, USA, October 1997.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1998

Authors and Affiliations

  • Radosław Sikora
    • 1
  • Władysław Skarbek
    • 2
  1. 1.Institute of MathematicsPolish Academy of SciencesPoland
  2. 2.Department of Electronics and Information TechnologyWarsaw University of TechnologyWarsaw

Personalised recommendations