Instabilities in Kohonen's self-organizing feature map
- 7 March 1994
- journal article
- Published by IOP Publishing in Journal of Physics A: General Physics
- Vol. 27 (5) , 1665-1681
- https://doi.org/10.1088/0305-4470/27/5/029
Abstract
The topology-preserving representation of a rectangular part of space onto a square network of formal neurons is studied using the Kohonen algorithm. Linear stability analysis shows that there is a critical ratio for the sides of the rectangle. For larger ratios the map becomes unstable. The value of the critical ratio depends on the actual shape of the adjustment function. The problems cannot be scaled away in the case of inhomogeneously sampled input space. The results of the analysis are compared with computer simulations.Keywords
This publication has 12 references indexed in Scilit:
- Topological maps on Ising spin networksPhysica A: Statistical Mechanics and its Applications, 1992
- Self-organizing maps: stationary states, metastability and convergence rateBiological Cybernetics, 1992
- Mathematical foundations of neurocomputingProceedings of the IEEE, 1990
- Convergence properties of Kohonen's topology conserving maps: fluctuations, stability, and dimension selectionBiological Cybernetics, 1988
- On the stationary state of Kohonen's self-organizing sensory mappingBiological Cybernetics, 1986
- Self-organized formation of topologically correct feature mapsBiological Cybernetics, 1982
- Dynamics of pattern formation in lateral-inhibition type neural fieldsBiological Cybernetics, 1977
- How patterned neural connections can be set up by self-organizationProceedings of the Royal Society of London. B. Biological Sciences, 1976
- A mathematical theory of the functional dynamics of cortical and thalamic nervous tissueBiological Cybernetics, 1973
- Self-organization of orientation sensitive cells in the striate cortexBiological Cybernetics, 1973