CRITICALLY IN THE ONE-DIMENSIONAL KOHONEN NEURAL MAP

被引：3

作者：

CSABAI, I ^{[1
]}

GESZTI, T ^{[1
]}

VATTAY, G ^{[1
]}

机构：

[1] EOTVOS LORAND UNIV, DEPT SOLID STATE PHYS, H-1088 BUDAPEST, HUNGARY

来源：

PHYSICAL REVIEW A | 1992年 / 46卷 / 10期

关键词：

D O I：

10.1103/PhysRevA.46.R6181

中图分类号：

O43 [光学];

学科分类号：

070207 ; 0803 ;

摘要：

In the marginally stable ordered state of Kohonen's feature-map neural-network model the distribution of fluctuating distances between neighboring cells is found to be a self-similar Weierstrass-Mandelbrot-type function with a nontrivial scaling exponent. The relationship among the quantities describing the distribution is discussed in terms of a balance between a deterministic multiplicative and a stochastic additive process, described by a Perron-Frobenius operator. Two regions of the Kohonen learning parameter alpha, separated by alpha(c) almost-equal-to 0.63, differ in the character of both fluctuation and ordering, the latter being fastest close to alpha(c).

引用

页码：R6181 / R6184

页数：4