Title :
Convergence of one-dimensional self-organizing map
Author :
Sum, John ; Chan, Lai-Wan
Author_Institution :
Dept. of Comput. Sci., Chinese Univ. of Hong Kong, Shatin, Hong Kong
Abstract :
Analyzes the convergence property of the one-dimensional self-organizing map (SOM). The key of the proof is the application of Ljung´s theorem [1977]. With the aid of the theorem, the authors can conclude that convergence of the one dimensional self-organizing map is almost certain if the following conditions are fulfilled, (i) the map is initial in order, (ii) the neighborhood interacting function (NIF) is non-increasing outward throughout the neighborhood interacting set (NIS) and (iii) the input distribution is stationary. Note that these conditions are less restrictive than those obtained previously in two folds: (i) there is no limit on the size of the NIS and (ii) the input distribution is not required to be uniform
Keywords :
convergence of numerical methods; self-organising feature maps; Ljung´s theorem; convergence property; input distribution; neighborhood interacting function; neighborhood interacting set; one-dimensional self-organizing map; Application software; Computer science; Convergence; Equations; Neurons; Organizing; Stationary state; Stochastic processes;
Conference_Titel :
Speech, Image Processing and Neural Networks, 1994. Proceedings, ISSIPNN '94., 1994 International Symposium on
Print_ISBN :
0-7803-1865-X
DOI :
10.1109/SIPNN.1994.344960