Skip to main content
SpringerLink
Log in

Clustering in weight space of feedforward nets

  • Oral Presentations: Theory Theory IV: Generalization II
  • 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

We study symmetries of feedforward networks in terms of their corresponding groups and find that these groups naturally act on and partition weight space. We specify an algorithm to generate representative weight vectors in a specific fundamental domain. The analysis of the metric structure of the fundamental domain enables us to use the location information of weight vector estimates, e. g. for cluster analysis. This can be implemented efficiently even for large networks.

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. An Mei Chen, Haw-minn Lu, and Robert Hecht-Nielsen. On the geometry of feedforward neural network error surfaces. Neural Computation, 5(6):910–927, 1993.

    Google Scholar 

  2. Richard O. Duda and Peter E. Hart. Pattern Classification and Scene Analysis. Wiley, 1973.

    Google Scholar 

  3. Bradley Efron and Robert J. Tibshirani. An Introduction to the Bootstrap. Chapman & Hall, 1993.

    Google Scholar 

  4. Arnfried Ossen and Stefan M. Rüger. Weight space analysis and forecast uncertainty. Submitted to Journal of Forecasting, 1996.

    Google Scholar 

  5. Héctor J. Sussmann. Uniqueness of the weights for minimal feedforward nets with a given input-output map. Neural Networks, 5:589–593, 1992.

    Google Scholar 

  6. Halbert White. Artificial Neural Networks — Approximation & Learning Theory. Blackwell, Oxford, Cambridge, 1992.

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Informatik, Sekr. FR 5-9, Technische Universität Berlin, Franklinstr. 28/29, 10 587, Berlin, Germany

    Stefan M. Rüger & Arnfried Ossen

Authors
  1. Stefan M. Rüger
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Arnfried Ossen
    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

Rüger, S.M., Ossen, A. (1996). Clustering in weight space of feedforward nets. 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_18

Download citation

  • DOI: https://doi.org/10.1007/3-540-61510-5_18

  • 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