Qualitative behaviour of some simple networks

被引:27
作者
Feng, J
Hadeler, KP
机构
[1] UNIV MUNICH,INST MATH,D-8000 MUNICH,GERMANY
[2] UNIV TUBINGEN,TUBINGEN,GERMANY
来源
JOURNAL OF PHYSICS A-MATHEMATICAL AND GENERAL | 1996年 / 29卷 / 16期
关键词
D O I
10.1088/0305-4470/29/16/023
中图分类号
O4 [物理学];
学科分类号
0702 ;
摘要
Some classical neural network systems including the Hartline-Ratliff system, the Linsker system, and the general sigmoid dynamics, are reconsidered within a more general class of dynamical systems. For synchronous dynamics the existence, uniqueness, local and global stability of stationary points is investigated. For asynchronous dynamics a convergence theorem is proved. The application of the theory of quasimonotone flows leads to some insights so far not widespread in network theory.
引用
收藏
页码:5019 / 5033
页数:15
相关论文
共 34 条
[1]  
Amit DJ, 1989, MODELING BRAIN FUNCT, DOI DOI 10.1017/CBO9780511623257
[2]  
[Anonymous], 1979, NONNEGATIVE MATRICES
[3]  
[Anonymous], 1978, Lectures on optimization: theory and algorithms
[4]  
CEA J, 1971, OPTIMISATION THEORIE, P118
[5]   COMPETITION SYSTEMS WITH PERIODIC COEFFICIENTS - A GEOMETRIC APPROACH [J].
DEMOTTONI, P ;
SCHIAFFINO, A .
JOURNAL OF MATHEMATICAL BIOLOGY, 1981, 11 (03) :319-335
[6]  
Doob J. L., 1953, Stochastic processes, V101
[7]  
FENG J, 1993, P 1993 IEEE INT C NE, V3, P1516
[8]  
FENG J, 1994, ADV MATH, V23, P451
[9]  
FENG J, 1995, ADV NEURAL INFORMATI, V7, P319
[10]   On neurodynamics with limiter function and Linsker's developmental model [J].
Feng, JF ;
Pan, H ;
Roychowdhury, VP .
NEURAL COMPUTATION, 1996, 8 (05) :1003-1019