Advertisement

Identification of Visual Features Using a Neural Version of Exploratory Projection Pursuit

  • Emilio Corchado
  • Colin Fyfe
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 2464)

Abstract

We develop artificial neural networks which extract structure from visual data. We explore an extension of Hebbian Learning which has been called ɛ- Insensitive Hebbian Learning and show that it may be thought of as a special case of Maximum Likelihood Hebbian learning and investigate the resulting network with both real and artificial data. We show that the resulting network is able to identify a single orientation of bars from a mixture of horizontal and vertical bars and also it is able to identify local filters from video images.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    H.B. Barlow,. and, D.J. Tolhurst. Why Do You Have Edge Detectors, Optical Society of America, Technical Digest, 23, 171. (1992).Google Scholar
  2. 2.
    C.M. Bishop. Neural Networks for Pattern Recognition, Oxford, 1995.Google Scholar
  3. 3.
    D. Charles, and C. Fyfe. Modelling Multiple Cause Structure Using Rectification Constraints. Network: Computation in Neural Systems, 9:167–182, 1998.zbMATHCrossRefGoogle Scholar
  4. 4.
    D. Charles, and C. Fyfe, Rectified Gaussian Distribution and the Identification of Multiple Causes Structure in Data. ICANN 99, 1999.Google Scholar
  5. 5.
    E. Corchado, D. MacDonald and C. Fyfe, Maximum and Minimum Likelihood Hebbian Learning. Data Mining and Knowledge Discover. Submitted. 2002.Google Scholar
  6. 6.
    D.J. Field, What is the goal of sensory coding? Neural Computation 6, 559–60, 1994.CrossRefGoogle Scholar
  7. 7.
    P. Földiák, Models of Sensory Coding PhD thesis, University of Cambridge, 1992.Google Scholar
  8. 8.
    J. Friedman, and J. Tukey, A Projection Pursuit Algorithm for Exploratory Data Analysis. IEEE Transaction on Computers, (23): 881–890, 1974.zbMATHCrossRefGoogle Scholar
  9. 9.
    C. Fyfe, “PCA Properties of Interneurons”, From Neurobiology to Real World Computing, Proceedings of International Conference on Artificial on Artificial Neural Networks, ICAAN 93, pages 183–188, 1993.Google Scholar
  10. 10.
    C. Fyfe, Negative Feedback as an Organising Principle for Artificial Neural Networks, PhD Thesis, Strathclyde University, 1995.Google Scholar
  11. 11.
    C. Fyfe, and R. Baddeley, Non-linear data structure extraction using simple Hebbian networks, Biological Cybernetics 72(6), p533–541, 1995.zbMATHCrossRefGoogle Scholar
  12. 12.
    C. Fyfe, A Scale Invariant Map. Network: Computing in Neural Systems, 7: pp 269–275, 1996.CrossRefGoogle Scholar
  13. 13.
    C. Fyfe, A Neural Network for PCA and Beyond, Neural Processing Letters, 6:33–41, 1997.CrossRefGoogle Scholar
  14. 14.
    D. Fyfe and C. Charles. Using Noise to Form a Minimal Overcomplete Basis, ICANN 99. 1999.Google Scholar
  15. 15.
    C. Fyfe and E. Corchado. Maximum Likelihood Hebbian Rules. European Symposium on Artificial Neural Networks. Esann 2002, 2002.Google Scholar
  16. 16.
    C. Fyfe, and D. MacDonald, ɛ-Insensitive Hebbian learning, Neuro Computing, 2001.Google Scholar
  17. 17.
    Y. Han, and C. Fyfe, A General Class of Neural Networks for P.C.A and F.A. Pages 158–163. Intelligent Data Engineering and Automated Learning. IDEAL 2000, 2000.Google Scholar
  18. 18.
    A. Hyvärinen, Complexity Pursuit: Separating interesting components from time series. Neural Computation, 13: 883–898, 2001.zbMATHCrossRefGoogle Scholar
  19. 19.
    J. Karhunen, and J. Joutsensalo, Representation and Separation of Signals Using Nonlinear PCA Type Learning, Neural Networks, 7:113–127, 1994.CrossRefGoogle Scholar
  20. 20.
    E. Oja, Neural Networks, Principal Components and Subspaces, International Journal of Neural Systems, 1:61–68, 1989.CrossRefMathSciNetGoogle Scholar
  21. 21.
    A.J. Smola, and. B. Scholkopf, A Tutorial on Support Vector Regression. Technical Report NC2-TR-1998-030, NeuroCOLT2 Technical Report Series. 1998.Google Scholar
  22. 22.
    J.H. Van Hateren, and A. Van der Schaaf, Independent Component Filters of Natural Images Compared with Simple Cells in Primary Visual Cortex. Proceedings of The Royal Society. London. B 265, 359–366, 1998.Google Scholar
  23. 23.
    L Xu. “Least Mean Square Error Reconstruction for Self-Organizing Nets”, Neural Networks, Vol. 6, pp. 627–648, 1993.CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2002

Authors and Affiliations

  • Emilio Corchado
    • 1
  • Colin Fyfe
    • 2
  1. 1.Area de Lenguajes y Sist. Informáticos. Departamento de Ingenieria CivilUniversidad de BurgosSpain
  2. 2.Applied Computational Intelligence Research UnitThe University of PaisleyScotland

Personalised recommendations