Clustering properties of hierarchical self-organizing maps |
| |
Authors: | Jouko Lampinen Erkki Oja |
| |
Affiliation: | (1) Department of Information Technology, Lappeenranta University of Technology, P.O. Box 20, SF-53851 Lappeenranta, Finland |
| |
Abstract: | A multilayer hierarchical self-organizing map (HSOM) is discussed as an unsupervised clustering method. The HSOM is shown to form arbitrarily complex clusters, in analogy with multilayer feedforward networks. In addition, the HSOM provides a natural measure for the distance of a point from a cluster that weighs all the points belonging to the cluster appropriately. In experiments with both artificial and real data it is demonstrated that the multilayer SOM forms clusters that match better to the desired classes than do direct SOM's, classical k-means, or Isodata algorithms. |
| |
Keywords: | cluster analysis self-organizing maps neural networks |
本文献已被 SpringerLink 等数据库收录! |
|