Geometrical Selection of Important Inputs with Feedforward Neural Networks

  • F. Rossi
Conference paper


In this paper, we introduce a method that allows to evaluate efficiently the ‘importance’ of each coordinate of the input vector of a neural network. This measurement can be used to obtain information about the studied data. It can also be used to suppress irrelevant inputs in order to speed up the classification process conducted by the network.


Mutual Information Input Vector Feedforward Neural Network Wavelet Network Irrelevant Input 
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]
    R. Battiti. Using Mutual Information for Selecting Features in Supervised Neural Net Learning. IEEE Trans. On Neural Networks, 5(4):537–550, July 1994.CrossRefGoogle Scholar
  2. [2]
    T. Cibas, F. Fogelman-Soulié, P. Gallinari, and S. Raudys. Variable selection with neural networks. Neurocomputing, 8(12):223–248, 1996.CrossRefGoogle Scholar
  3. [3]
    R.O. Duda and P.E. Hart. Pattern Classification and Scene Analysis. Wiley, New York, 1973.MATHGoogle Scholar
  4. [4]
    C. Gégout, B. Girau and F. Rossi. Generic Back-Propagation in Arbitrary Feedforward Neural Networks. In D.W. Pearson, N.C. Steele, and R.F. Albrecht, editors, Int. Conf. on Artificial Neural Networks and Genetic Algorithms, pages 168–171, Als, April 1995. Springer Verlag.Google Scholar
  5. [5]
    A.J. Miller. Subset Selection in Regression. Chapman and Hall, 1990.Google Scholar
  6. [6]
    W.H. Press, S.A. Teukolsky, W.T. Vetterling, and B.P. Flannery. Numerical Recipes in C. Cambridge University Press, second edition, 1992.Google Scholar
  7. [7]
    K.L. Priddy, S.K. Rogers, D.W. Ruck, G.L. Tarr, and M. Kabrisky. Bayesian selection of important features for feedforward neural networks. Neurocomputing, 5:91–103, 1993.CrossRefGoogle Scholar
  8. [8]
    F. Rossi. Attribute suppression with multi-layer perceptron. In CESA Multiconference, Symposium on Robotics and Cybernetics, pages 542–547, Lille-France, July 1996. IMACS.Google Scholar
  9. [9]
    H. White. Learning in Artificial Neural Networks: A Statistical Perspective. Neural Computation, 1(4):425–464, 1989.CrossRefGoogle Scholar
  10. [10]
    Q. Zhang and A. Benveniste. Wavelet networks. IEEE Trans. On Neural Networks, 3(6):889–898, November 1992.CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Wien 1998

Authors and Affiliations

  • F. Rossi
    • 1
    • 2
  2. 2.Universit Paris-IX Dauphine, UFR MDParisFrance

Personalised recommendations