Skip to main content
SpringerLink
Log in

Architecture selection through statistical sensitivity analysis

  • Oral Presentations: Applications Scientific Applications I
  • Conference paper
  • First Online:
Artificial Neural Networks — ICANN 96 (ICANN 1996)

Part of the book series: Lecture Notes in Computer Science ((LNCS,volume 1112))

Included in the following conference series:

Abstract

In this paper, a method for pruning hidden neurones is presented, and illustrated on two different problems. It is based on the statistical study of the derivatives of the outputs of the model with regards to each hidden neurone. We claim that if the model is not using a particular neurone to estimate its outputs, then the corresponding sensitivities will have a low degree of significance. This article is an extension of a previous work dedicated to the selection of input variables. We consider each hidden layer as the input layer of a smaller network made of all the remaining layers between this one and the output. The aim of this analysis is the selection of an appropriate subset of neurones for each layer, to finally obtain a more parsimonious model.

The work of T. Czernichow has been supported by a CIFRE grant N∘91/93 with Electricité de France, Direction des Etudes et Recherches (EDF-DER).

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution

Institutional subscriptions

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. T. Czernichow, A. Muñoz, “Variable Selection through Statistical Sensitivity Analysis: Application to feedforward and recurrent networks.,” INT-SIM, http://www-sim.int-evry.fr/People/Czernichow.html, Technical Report 95-07-01, 1995.

    Google Scholar 

  2. B. Dorizzi, G. Pellieux, F. Jacquet, T. Czernichow, A. Muñoz, “Selecting the relevant variables to forecast the French T-Bond,” presented at Third Chemical Bank/Imperial College Conference on Forecasting Financial Markets, London, 1996.

    Google Scholar 

  3. P. Cardaliaguet, G. Euvrard, “Approximation of a Function and its Derivatives with a Neural Network,” Neural Networks, vol. 5, pp. 207–220, 1992.

    Google Scholar 

  4. K. Hornik, M. Stinchcombe, H. White, “Universal Approximation of an unknown Mapping and its Derivatives Using Multilayer Feedforward Networks,” Neural Networks, vol. 3, pp. 551–560, 1990.

    Google Scholar 

  5. A. R. Gallant, H. White, “On learning the derivatives of an unknown Mapping with Multilayer Feedforward Networks,” Neural Networks, vol. 5, pp. 129–138, 1992.

    Google Scholar 

  6. D. G. Luenberger, Linear and non-linear programming, 2nd ed: Adddison-Wesley, 1984.

    Google Scholar 

  7. C. D. Liu, J. Nocedal, “On the limited memory BFGS method for large scale optimization,” Mathematical programming, vol. 45, pp. 503–528, 1989.

    Google Scholar 

  8. T. Czernichow, A. Piras, K. Imhof, P. Caire, Y. Jaccard, B. Dorizzi, A. Germond, “Short Term Electrical Load Forecasting with Artificial Neural Networks,” Int. Journal of Eng. Int. Syst., To appear, 1996.

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Electricité de France (EDF-DER), 1 Av. du Général De Gaulle, Clamart, France

    Thomas Czernichow

  2. Département EPH, Institut National des Télécommunications, 9 Av Charles Fourier, 91011, Evry Cedex, France

    Thomas Czernichow

Authors
  1. Thomas Czernichow
    View author publications

    You can also search for this author in PubMed Google Scholar

Editor information

Christoph von der Malsburg Werner von Seelen Jan C. Vorbrüggen Bernhard Sendhoff

Rights and permissions

Reprints and permissions

Copyright information

© 1996 Springer-Verlag Berlin Heidelberg

About this paper

Cite this paper

Czernichow, T. (1996). Architecture selection through statistical sensitivity analysis. In: von der Malsburg, C., von Seelen, W., Vorbrüggen, J.C., Sendhoff, B. (eds) Artificial Neural Networks — ICANN 96. ICANN 1996. Lecture Notes in Computer Science, vol 1112. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-61510-5_33

Download citation

  • DOI: https://doi.org/10.1007/3-540-61510-5_33

  • Published:

  • Publisher Name: Springer, Berlin, Heidelberg

  • Print ISBN: 978-3-540-61510-1

  • Online ISBN: 978-3-540-68684-2

  • eBook Packages: Springer Book Archive

Publish with us

Policies and ethics

Search

Navigation