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.
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
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.
Richard O. Duda and Peter E. Hart. Pattern Classification and Scene Analysis. Wiley, 1973.
Bradley Efron and Robert J. Tibshirani. An Introduction to the Bootstrap. Chapman & Hall, 1993.
Arnfried Ossen and Stefan M. Rüger. Weight space analysis and forecast uncertainty. Submitted to Journal of Forecasting, 1996.
Héctor J. Sussmann. Uniqueness of the weights for minimal feedforward nets with a given input-output map. Neural Networks, 5:589–593, 1992.
Halbert White. Artificial Neural Networks — Approximation & Learning Theory. Blackwell, Oxford, Cambridge, 1992.
Author information
Authors and Affiliations
Editor information
Rights 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