Global asymptotic stability of a class of feedback neural networks with an application to optimization problems

被引：0
作者：
Zhaoshu Feng
Anthony N. Michel
机构：
[1] University of Notre Dame,Department of Electrical Engineering
来源：
Circuits, Systems and Signal Processing | 1998年 / 17卷
关键词：
Neural Network; Asymptotic Stability; Stability Testing; Stability Theory; Unique Equilibrium;
D O I：
暂无
中图分类号：
学科分类号：
摘要：
By applying results from homotopy theory, new conditions are obtained for the existence and uniqueness of an equilibrium for a class of continuous-time feedback neural networks which contains the Hopfield model as a special case. Next, new criteria are established for the global asymptotic stability of the unique equilibrium of this class of neural networks by utilizing Lur'e-type Lyapunov functions and the stability theory for systems of differential inequalities. Several practical stability testing conditions are given. As a special case, criteria are derived for the global asymptotic stability of Hopfield neural networks. This is followed by a robustness analysis of the class of neural networks considered. The results obtained are then applied to an optimization problem.
引用
收藏
页码：219 / 241
页数：22
相关论文
共 79 条
  • [1] Avitabile G.(1991)On a class of nonsymmetrical neural networks with application to ADC IEEE Trans. Circuits Syst. 38 202-209
  • [2] Forti M.(1983)Matrix diagonal stability and its implications SIAM J. Algebraic Discrete Methods 4 377-382
  • [3] Manetti S.(1996)Existence and stability of a unique equilibrium in continuous-valued discrete-time asynchronous Hopfield neural networks IEEE Trans. Neural Networks 7 620-628
  • [4] Marini A.(1992)The construction of arbitrary stable dynamics in nonlinear neural networks Neural Networks 5 83-103
  • [5] Berman D.(1983)Absolute stability of global pattern formation and parallel memory storage by competitive neural networks IEEE Trans. Syst., Man and Cybern 13 815-826
  • [6] Hershkowitz A.(1966)Some generalizations for positive definiteness and monotonicity Numer. Math. 9 163-172
  • [7] Bhaya E.(1994)Necessary and sufficient condition for absolute stability of neural networks IEEE Trans. Circuits Syst.—I 41 491-494
  • [8] Kaszkurewicz V. S.(1995)New conditions for global stability of neural networks with application to linear and quadratic programming problems IEEE Trans. Circuits Systs.—I 42 354-366
  • [9] Kozyakin M. A.(1997)Computing the number, location, and stability of fixed points of Poincaré maps IEEE Trans. Circuits Syst.—I 44 303-311
  • [10] Cohen M. A.(1971)Some results on existence and uniqueness of solutions of nonlinear networks IEEE Trans. Circuit Theory 18 501-506
12345678