STABILITY AND DYNAMICS OF DELAY-TYPE GENERAL AND CELLULAR NEURAL NETWORKS

被引:231
作者
ROSKA, T
WU, CW
BALSI, M
CHUA, LO
机构
[1] Electronics Research Laboratory, Department of Electrical Engineering and Computer Sciences, University of California, Berkeley, CA
关键词
D O I
10.1109/81.153647
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
Delay-type general neural networks and cellular neural networks (CNN's) proved to be important in different application areas including motion detection. In this paper, several stability results and additional properties of the delay-type neural network and CNN dynamics are proved. As a typical example, it is proved that if the feedback and delayed feedback matrices A and A(tau) are non-negative and the sum (A + A(tau)) is irreducible, then the neural network is stable.
引用
收藏
页码:487 / 490
页数:4
相关论文
共 13 条
[1]   CELLULAR NEURAL NETWORKS - APPLICATIONS [J].
CHUA, LO ;
YANG, L .
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS, 1988, 35 (10) :1273-1290
[2]   CELLULAR NEURAL NETWORKS - THEORY [J].
CHUA, LO ;
YANG, L .
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS, 1988, 35 (10) :1257-1272
[3]  
CHUA LO, 1991, ERL UCBERL M9131 U C
[4]   A CNN CHIP FOR CONNECTED COMPONENT DETECTION [J].
CRUZ, JM .
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS, 1991, 38 (07) :812-817
[5]  
Driver RD, 1977, APPL MATH SCI, V20
[7]  
ROSKA T, 1990, P IEEE INT WORKSHOP, P12
[8]  
ROSKA T, 1991, UCBERL M91110 U CAL
[9]  
ROSKA T, IN PRESS INT J CIRCU
[10]   MONOTONE SEMIFLOWS GENERATED BY FUNCTIONAL-DIFFERENTIAL EQUATIONS [J].
SMITH, H .
JOURNAL OF DIFFERENTIAL EQUATIONS, 1987, 66 (03) :420-442