Abstract
The behavior of self-organizing feature maps is critically dependent on parameters such as lateral connection radius, lateral inhibition intensity, and network size. With no theoretical guidelines for the choice of these parameters, they are usually selected through a trial-and-error process. In order to provide heuristic guidelines for future model designers as well as to give insight into which model features are responsible for specific aspects of maps, we systematically varied these parameters and studied their effects on the properties of a self-organizing feature map. The connectivity radius was found to determine the size of activation clusters quadratically. As the intensity of lateral inhibition was varied, feature patterns varied from stripe-like to clusters in the map, with other intermediate patterns also occurring. The number of clusters of each feature increased nonlinearly as the network size increased.
Similar content being viewed by others
References
T.Kohonen, Self-Organization and Associative Memory, Springer-Verlag: Berlin, 1988.
S.Cho and J.Reggia, “Map formation in proprioceptive cortex”, International Journal of Neural Systems, Vol. 5, pp. 87–101, 1994.
T.Carew and C.Ghez, “Muscles and muscle receptors”, in E.Kandel and J.Schwartz (eds) Principles of Neural Science, pp. 443–456, Elsevier: New York, 1985.
C.von derMalsburg, “Self-organization of orientation sensitive cells in the striate cortex”, Kybernetic, Vol. 14, pp. 85–100, 1973.
S.Cho and J.Reggia, “Learning competition and cooperation”, Neural Computation, Vol. 5, pp. 242–259, 1993.
J.Reggia, C.L.D'Autrechy, G.Sutton and M.Weinrich, “A competitive distribution theory of neocortical dynamics”, Neural Computation, Vol. 4, pp. 287–317, 1992.
R.Linsker, “From basic network principles to neural architecture: emergence of orientation columns”, Proceedings of National Academy of Science, Vol. 83, pp. 8779–8783, 1986.
J.Reggia and D.Montgomery, “A computational model of visual hallucinations in migraine”, Computers in Biology and Medicine, Vol. 26, pp. 133–141, 1996.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Cho, S., Jang, M. & Reggia, J.A. Effects of varying parameters on properties of self-organizing feature maps. Neural Process Lett 4, 53–59 (1996). https://doi.org/10.1007/BF00454846
Issue Date:
DOI: https://doi.org/10.1007/BF00454846