EXPONENTIAL STABILITY AND TRAJECTORY BOUNDS OF NEURAL NETWORKS UNDER STRUCTURAL VARIATIONS

被引：21

作者：

GRUJIC, LT ^{[1
]}

MICHEL, AN ^{[1
]}

机构：

[1] UNIV NOTRE DAME, DEPT ELECT & COMP ENGN, NOTRE DAME, IN 46556 USA

来源：

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS | 1991年 / 38卷 / 10期

关键词：

D O I：

10.1109/31.97538

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：

The dynamic behavior of neural networks under arbitrary unknown structural perturbations depends essentially on the compatibility/incompatibility of input variables in these networks. Estimates of the upper bounds of the motions of neural networks of either type and exponential stability of compatible neural networks are established by using three different forms of Lyapunov functions. Moreover, conditions for the maximum possible estimate of the domain of structural exponential stability are determined. All new concepts such as compatible/incompatible neural networks and structural exponential stability are defined. The obtained results are in the form suitable for straightforward applications.

引用

页码：1182 / 1192

页数：11

共 17 条

[1]

Fiedler M., 1962, CZECH MATH J, V12, P382

[2]

Grujic Lj. T, 1987, LARGE SCALE SYSTEMS

[3]

GRUJIC LT, 1990, 1990 IEEE INTERNATIONAL SYMP ON CIRCUITS AND SYSTEMS, VOLS 1-4, P391, DOI 10.1109/ISCAS.1990.112054

[4]

HOPFIELD JJ, 1985, BIOL CYBERN, V52, P141

[5] NEURONS WITH GRADED RESPONSE HAVE COLLECTIVE COMPUTATIONAL PROPERTIES LIKE THOSE OF 2-STATE NEURONS [J].

HOPFIELD, JJ .

PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA-BIOLOGICAL SCIENCES, 1984, 81 (10) :3088-3092

[6]

HOPFIELD JJ, 1988, IEEE CIRCUITS DEVICE, P3

[7] QUALITATIVE-ANALYSIS AND SYNTHESIS OF A CLASS OF NEURAL NETWORKS [J].

JIAN, HL ;

MICHEL, AN ;

POROD, W .

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS, 1988, 35 (08) :976-986

[8]

Kamke E., 1932, ACTA MATH, V58, P57, DOI DOI 10.1007/BF02547774

[9] ANALYSIS AND SYNTHESIS OF A CLASS OF NEURAL NETWORKS - LINEAR-SYSTEMS OPERATING ON A CLOSED HYPERCUBE [J].

LI, JH ;

MICHEL, AN ;

POROD, W .

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS, 1989, 36 (11) :1405-1422

[10] ANALYSIS AND SYNTHESIS OF A CLASS OF NEURAL NETWORKS - VARIABLE STRUCTURE SYSTEMS WITH INFINITE GAIN [J].

LI, JH ;

MICHEL, AN ;

POROD, W .

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS, 1989, 36 (05) :713-731

← 1 2 →