Loading...
Please wait, while we are loading the content...
Similar Documents
Simplexes, Multi-Dimensional Scaling and Self-Organized Mapping (1996)
| Content Provider | CiteSeerX |
|---|---|
| Author | Duch, Wlodzislaw Naud, Antoine |
| Description | In Proceedings of The "8th Joint Eps-Aps International Conference on Physics Computing ’96 |
| Abstract | The self-organizing map (SOM) of Kohonen is one of the most successful models of unsupervised learning. Its popularity is partially due to the visualization (topography preservation) of relations among clusters in high-dimensional input space. SOM learns slowly, especially in the initial phase, and the preservation of topography by SOM maps is not based on any quantitative criteria. We have obtained the best possible two-dimensional representation of simplexes in spaces of up to 20 dimensions, minimizing the error function measuring the unavoidable distortion of the original input space topography. This two-dimensional representation is used to select neurons during initialization of the SOM network. After such initialization in the learning phase a small radius of the neighborhood function is sufficient to obtain quick convergence with minimal topological distortions. 1 Introduction The self-organizing mapping (SOM) algorithm [1] is usually presented as a particular type of artifici... |
| File Format | |
| Language | English |
| Publisher Date | 1996-01-01 |
| Access Restriction | Open |
| Subject Keyword | Self-organized Mapping Multi-dimensional Scaling Unsupervised Learning Som Map Initial Phase Successful Model High-dimensional Input Space Error Function Topography Preservation Quantitative Criterion Self-organizing Map Minimal Topological Distortion Unavoidable Distortion Self-organizing Mapping Two-dimensional Representation Particular Type Learning Phase Small Radius Som Network Possible Two-dimensional Representation Original Input Space Topography Neighborhood Function Quick Convergence |
| Content Type | Text |
| Resource Type | Technical Report |
