Analysing a self-organising algorithm

被引：3
作者：
Flanagan, JA
机构：
[1] Circuits and Systems Group, Department of Electrical Engineering, Swiss Federal Institute of Technology, CH-1015, Lausanne
来源：
NEURAL NETWORKS | 1997年 / 10卷 / 05期
关键词：
self-organisation; ordinary differential equation method; connectedness;
D O I：
10.1016/S0893-6080(96)00114-1
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
A self-organising algorithm is described, which is a generalisation of an algorithm proposed by Cottrell and Fort. The algorithm is analysed in a more general fashion using the ordinary differential equation method (ODE) of stochastic approximation theory. The result is a set of linear equations which the stationary state of the neuron weights must satisfy. Several features of the algorithm are analysed including the conditions necessary for the existence of a single stationary point as well as the configuration of the stationary state. It is shown what conditions favour the convergence of the neuron weights towards an organised configuration. (C) 1997 Elsevier Science Ltd.
引用
收藏
页码：875 / 883
页数：9
相关论文
共 14 条
[1]  
BENEVENISTE A, 1990, APPL MATH, V22
[2]   SELF-ORGANIZATION AND AS CONVERGENCE OF THE ONE-DIMENSIONAL KOHONEN ALGORITHM WITH NONUNIFORMLY DISTRIBUTED STIMULI [J].
BOUTON, C ;
PAGES, G .
STOCHASTIC PROCESSES AND THEIR APPLICATIONS, 1993, 47 (02) :249-274
[3]  
Clark D. S, 1978, STOCHASTIC APPROXIMA, V26
[4]  
COTTRELL M, 1987, ANN I H POINCARE-PR, V23, P1
[5]   A STOCHASTIC-MODEL OF RETINOTOPY - A SELF-ORGANIZING PROCESS [J].
COTTRELL, M ;
FORT, JC .
BIOLOGICAL CYBERNETICS, 1986, 53 (06) :405-411
[6]  
COTTRELL M, 1994, EUR S ART NEUR NETW
[7]  
GANTMACHER FR, 1966, THEORIE MATRICES
[8]  
Kaplan W., 1981, Advanced Mathematics for Engineers
[9]  
Kohonen T., 1995, SELF ORG MAPS
[10]   ANALYSIS OF RECURSIVE STOCHASTIC ALGORITHMS [J].
LJUNG, L .
IEEE TRANSACTIONS ON AUTOMATIC CONTROL, 1977, 22 (04) :551-575
12