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. |
Year | DOI | Venue |
---|---|---|
1996 | 10.1007/3-540-61510-5_18 | ICANN |
Keywords | Field | DocType |
feedforward nets,weight space,cluster analysis | k-medians clustering,Topology,Correlation clustering,Computer science,Fundamental domain,Weight,Partition (number theory),Cluster analysis,Homogeneous space,Feed forward | Conference |
ISBN | Citations | PageRank |
3-540-61510-5 | 4 | 0.88 |
References | Authors | |
2 | 2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Stefan M. Rüger | 1 | 499 | 51.53 |
Arnfried Ossen | 2 | 7 | 1.72 |