An Empirical Study on the Robustness of SOM in Preserving Topology with Respect to Link Density
Practical implementations of SOM model require parallel and synchronous operation of the network during each iteration in the training stage. However this implicitly implies existence of some communication link between the winner neuron and all other neurons so that update can be induced to the neighboring neurons. In the current paper we report the results of an empirical study on the retention of topology preservation property of the SOM when such links become partially absent, so that during a training iteration not all the neighbors of the winner may be updated. We quantify our results using three different indexes for topology preservation.
KeywordsSOM topology preservation link density
Unable to display preview. Download preview PDF.
- 2.Kohonen, T.: Self-Organization and Associative Memory. Springer, Heidelberg (1989)Google Scholar
- 3.Anderson, J.A., Pellionisz, A.: Neurocomputing 2: Directions for Research. MIT Press, Cambridge (1990)Google Scholar
- 5.Kohonen, T.: Automatic formation of topological maps of patterns in a selforganizing sysyem. In: Proc. 2nd Scandinavian Conf. on Image Analysis, pp. 214–220 (1981)Google Scholar
- 9.Laha, A., Pal, N.R.: On different variants of self-organizing feature map and their property. In: Proc. of the IEEE Hong Kong Symposium on Robotics and Controls, vol. 1, pp. I344–I349 (1999)Google Scholar
- 10.Kendall, M., Gibbons, J.D.: Rank Correlation Coefficient. Edward Arnold (1990)Google Scholar