An analysis of Kohonen's self-organizing maps using a system of energy functions
- 1 December 1990
- journal article
- research article
- Published by Springer Nature in Biological Cybernetics
- Vol. 64 (2) , 155-164
- https://doi.org/10.1007/bf02331345
Abstract
In this paper a new method for analyzing Kohonen's self-organizing feature maps is presented. The method makes use of a system of energy functions, one energy function for each processing unit. It is shown that the training process is equivalent to minimizing each energy function subject to constraints. The analysis is used to prove the formation of topologically correct maps when the inherent dimensionality of the input patterns matches that of the network. The energy equations can be used to compute the steady-state weight values of the network. In addition, the analysis allows bounds on the training parameters to be determined. Finally, examples of energy landscapes are presented to graphically show the behavior of the network.Keywords
This publication has 10 references indexed in Scilit:
- Self-organisation: a derivation from first principles of a class of learning algorithmsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1989
- A self-organizing neural network for classifying sequencesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1989
- Convergence properties of Kohonen's topology conserving maps: fluctuations, stability, and dimension selectionBiological Cybernetics, 1988
- The 'neural' phonetic typewriterComputer, 1988
- Kohonen's self-organizing maps: exploring their computational capabilitiesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1988
- On the stationary state of Kohonen's self-organizing sensory mappingBiological Cybernetics, 1986
- Analysis of a simple self-organizing processBiological Cybernetics, 1982
- Neural networks and physical systems with emergent collective computational abilities.Proceedings of the National Academy of Sciences, 1982
- Self-organized formation of topologically correct feature mapsBiological Cybernetics, 1982
- Self-organization of orientation sensitive cells in the striate cortexBiological Cybernetics, 1973