DISCRETE-TIME VERSUS CONTINUOUS-TIME MODELS OF NEURAL NETWORKS

被引：33
作者：
WANG, X
BLUM, EK
机构：
[1] Department of Mathematics, University of Southern California, Los Angeles
来源：
JOURNAL OF COMPUTER AND SYSTEM SCIENCES | 1992年 / 45卷 / 01期
关键词：
D O I：
10.1016/0022-0000(92)90038-K
中图分类号：
TP3 [计算技术、计算机技术];
学科分类号：
0812 ;
摘要：
In mathematical modeling, very often discrete-time (DT) models are taken from, or can be viewed as numerical discretizations of, certain continuous-time (CT) models. In this paper, a general criterion, the asymptotic consistency criterion, for these DT models to inherit the dynamical behavior of their CT counterparts is derived. Detailed instances of this criterion are established for several classes of neural networks. © 1992.
引用
收藏
页码：1 / 19
页数：19
相关论文
共 31 条
[1]   CHARACTERISTICS OF RANDOM NETS OF ANALOG NEURON-LIKE ELEMENTS [J].
AMARI, S .
IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS, 1972, SMC2 (05) :643-&
[2]  
ANDERSON JA, 1990, NEUROCOMPUTING F RES, V1
[3]  
ANDERSON JA, 1990, NEUROCOMPUTING F RES, V2
[4]  
ARBIB M, 1989, METAPHORIAL BRAIN, V2
[5]  
Atiya A., 1989, International Journal of Neural Systems, V1, P103, DOI 10.1142/S0129065789000025
[6]   MATHEMATICAL ASPECTS OF OUTER-PRODUCT ASYNCHRONOUS CONTENT-ADDRESSABLE MEMORIES [J].
BLUM, EK .
BIOLOGICAL CYBERNETICS, 1990, 62 (04) :337-348
[7]  
BLUM EK, IN PRESS NEURAL NETW
[8]  
BLUM EK, 1972, NUMERICAL ANAL COMPU
[9]  
Cowan J., 1968, NEURAL NETWORKS, P181
[10]  
Davis PJ, 1979, CIRCULANT MATRICES
1234