Stability of asymmetric Hopfield networks

被引：121

作者：

Chen, TP ^{[1
]}

Amari, SI

机构：

[1] Fudan Univ, Inst Math, Lab Nonlinear Sci, Shanghai 200433, Peoples R China

[2] RIKEN, Brain Sci Inst, Wako, Saitama 35101, Japan

来源：

IEEE TRANSACTIONS ON NEURAL NETWORKS | 2001年 / 12卷 / 01期

基金：

中国国家自然科学基金;

关键词：

recurrent neural networks; stability;

D O I：

10.1109/72.896806

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

In this paper, we discuss dynamical behaviors of recurrently asymmetrically connected neural networks in detail. We propose an effective approach to study global and local stability of the networks. Many of well known existing results are unified in our framework, which gives much better test conditions for global and local stability. Sufficient conditions for the uniqueness of the equilibrium point and its stability conditions are given, too.

引用

页码：159 / 163

页数：5

共 17 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] CHARACTERISTICS OF RANDOMLY CONNECTED THRESHOLD-ELEMENT NETWORKS AND NETWORK SYSTEMS [J].

AMARI, SI .

PROCEEDINGS OF THE INSTITUTE OF ELECTRICAL AND ELECTRONICS ENGINEERS, 1971, 59 (01) :35-&

[3] 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

[4] Stability analysis of dynamical neural networks [J].

Fang, YG ;

Kincaid, TG .

IEEE TRANSACTIONS ON NEURAL NETWORKS, 1996, 7 (04) :996-1006

[5] NECESSARY AND SUFFICIENT CONDITION FOR ABSOLUTE STABILITY OF NEURAL NETWORKS [J].

FORTI, M ;

MANETTI, S ;

MARINI, M .

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS I-REGULAR PAPERS, 1994, 41 (07) :491-494

[6] CONVERGENT ACTIVATION DYNAMICS IN CONTINUOUS-TIME NETWORKS [J].

HIRSCH, MW .

NEURAL NETWORKS, 1989, 2 (05) :331-349

[7] COMPUTING WITH NEURAL CIRCUITS - A MODEL [J].

HOPFIELD, JJ ;

TANK, DW .

SCIENCE, 1986, 233 (4764) :625-633

[8] 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

[9] 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

[10] ON A CLASS OF GLOBALLY STABLE NEURAL CIRCUITS [J].

KASZKUREWICZ, E ;

BHAYA, A .

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS I-FUNDAMENTAL THEORY AND APPLICATIONS, 1994, 41 (02) :171-174

← 1 2 →