Stability of Hopfield neural networks

被引：4

作者：

Boikov, IV ^{[1
]}

机构：

[1] Penza State Univ, Penza, Russia

来源：

AUTOMATION AND REMOTE CONTROL | 2003年 / 64卷 / 09期

关键词：

Differential Equation; Neural Network; Mechanical Engineer; System Theory; Stability Criterion;

D O I：

10.1023/A:1026056104067

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

A stability criterion for the Hopfield neural networks with continuous and discontinuous nonlinearities and operation described by nonlinear differential equations is formulated and is based on the sign of the logarithmic norm of a matrix.

引用

页码：1474 / 1487

页数：14

共 8 条

[1]

[Anonymous], 1967, LEKTSII MATEMATICHES

[2]

BORISOV YI, 1994, PRIBOROSTROENIE, P5

[3]

Daletskii Yu.L., 1970, Stability of Solutions of Differential Equations in a Banach Space

[4]

DUDNIKOV EE, 1999, AVTOMAT TELEMEKH, P33

[5]

Filippov A.F., 1988, MATH ITS APPL SOVIET, V18

[6]

GORBAN AN, 1996, NEIRONNYE SETI PERSO

[7] 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

[8]

PETROV BM, 1994, IZV VUZ RADIOELEKTR+, V37, P3

← 1 →