AN APPLICATION OF LIAPUNOV METHOD FOR THE ANALYSIS OF NEURAL NETWORKS

被引：1

作者：

NOLDUS, E ^{[1
]}

LOCCUFIER, M ^{[1
]}

机构：

[1] STATE UNIV GHENT,AUTOMAT CONTROL LAB,B-9052 ZWIJNAARDE,BELGIUM

来源：

JOURNAL OF COMPUTATIONAL AND APPLIED MATHEMATICS | 1994年 / 50卷 / 1-3期

关键词：

LIAPUNOV METHOD; STABILITY; NEURAL NETWORKS;

D O I：

10.1016/0377-0427(94)90318-2

中图分类号：

O29 [应用数学];

学科分类号：

070104 ;

摘要：

The stability is studied of a class of nonlinear dynamical systems which possess many nonlinearities and many equilibrium states. As a special case, the analyzed class of systems includes analog neural networks. Sufficient conditions for the nonoscillatory behaviour of these systems, in the form of frequency domain criteria, are presented. The main result is proved relying on a suitable Liapunov function which is subsequently used for the simultaneous computation of regions of attraction for each stable equilibrium.

引用

页码：425 / 432

页数：8

共 12 条

[1] ABSOLUTE STABILITY OF GLOBAL PATTERN-FORMATION AND PARALLEL MEMORY STORAGE BY COMPETITIVE NEURAL NETWORKS [J].

COHEN, MA ;

GROSSBERG, S .

IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS, 1983, 13 (05) :815-826

[2]

HASLER M, 1989, CR JOURNEES ELECTRON, P61

[3] 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

[4]

KEEN TK, 1991, NETWORK, V2, P85

[5]

LASALLE JP, 1967, DIFF EQUAT, P277

[6]

Noldus E., 1973, International Journal of Control, V17, P641, DOI 10.1080/00207177308932409

[7]

SILJAK DD, 1969, NONLINEAR SYSTEMS

[8]

Simpson PK, 1990, ARTIFICIAL NEURAL SY

[9]

SONTAG E, 1991, P WORKSHOP THEORETIC

[10]

UNBEHAUEN R, 1980, SYSTEMTHEORIE DARSTE

← 1 2 →