ON THE AS CONVERGENCE OF THE KOHONEN ALGORITHM WITH A GENERAL NEIGHBORHOOD FUNCTION
成果类型：
Article
署名作者：
Fort, Jean-Claude; Pages, Gilles
署名单位：
Universite de Lorraine; Sorbonne Universite
刊物名称：
ANNALS OF APPLIED PROBABILITY
ISSN/ISSBN：
1050-5164
DOI：
10.1214/aoap/1177004611
发表日期：
1995
页码：
1177-1216
关键词：
摘要：
Some existence and stability results for the equilibrium points of the one-dimensional Kohonen self-organizing neural network with two neighbors are extended to most nonincreasing neighborhood functions. All the functions mentioned in the neural literature are included. The assumption on the stimuli distribution is weakened, too. In the multidimensional setting, we derive from a general formula various stability and instability results.