Global exponential stability of recurrent neural networks for solving optimization and related problems

被引：60
|
作者：
Xia, YS [1 ]
Wang, J [1 ]
机构：
[1] Chinese Univ Hong Kong, Dept Automat & Comp Aided Engn, Hong Kong, Hong Kong, Peoples R China
来源：
IEEE TRANSACTIONS ON NEURAL NETWORKS | 2000年 / 11卷 / 04期
关键词：
global exponential stability; optimization problems; recurrent neural networks;
D O I：
10.1109/72.857782
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
Global exponential stability is a desirable property for dynamic systems. This paper studies the global exponential stability of several existing recurrent neural networks for solving linear programming problems, convex programming problems with interval constraints, convex programming problems with nonlinear constraints, and monotone variational inequalities. In contrast to the existing results on global exponential stability, the present results do not require additional conditions on the weight matrices of recurrent neural networks and improve some existing conditions for global exponential stability. Therefore, the stability results in this paper further demonstrate the superior convergence properties of the existing neural networks for optimization.
引用
收藏
页码：1017 / 1022
页数：6
相关论文
共 50 条
  • [41] Solving evolutionary problems using recurrent neural networks
    Petrasova, Iveta
    Karban, Pavel
    JOURNAL OF COMPUTATIONAL AND APPLIED MATHEMATICS, 2023, 426
  • [42] Global stability of interval recurrent neural networks
    袁铸钢
    刘志远
    裴润
    申涛
    JournalofBeijingInstituteofTechnology, 2012, 21 (03) : 382 - 386
  • [43] Global exponential stability of discrete-time neural networks for constrained quadratic optimization
    Tan, KC
    Tang, HJ
    Yi, Z
    NEUROCOMPUTING, 2004, 56 : 399 - 406
  • [44] Global asymptotic stability and global exponential stability of delayed cellular neural networks
    Liao, XXX
    Wang, J
    Zeng, ZG
    IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS II-EXPRESS BRIEFS, 2005, 52 (07) : 403 - 409
  • [45] Global exponential stability for recurrent neural networks with a general class of activation functions and variable delays
    Zhou, DM
    Zhang, LM
    Zhao, DF
    PROCEEDINGS OF 2003 INTERNATIONAL CONFERENCE ON NEURAL NETWORKS & SIGNAL PROCESSING, PROCEEDINGS, VOLS 1 AND 2, 2003, : 108 - 111
  • [46] Novel Global Exponential Stability Criterion for Recurrent Neural Networks with Time-Varying Delay
    Luo, Wenguang
    Wang, Xiuling
    Liu, Yonghua
    Lan, Hongli
    ABSTRACT AND APPLIED ANALYSIS, 2013,
  • [47] A generalized LMI-based approach to the global exponential stability of recurrent neural networks with delay
    Shen, Y
    Jiang, MH
    Liao, XX
    ADVANCES IN NEURAL NETWORKS - ISNN 2005, PT 1, PROCEEDINGS, 2005, 3496 : 114 - 119
  • [48] Global Exponential Stability for Complex-Valued Recurrent Neural Networks With Asynchronous Time Delays
    Liu, Xiwei
    Chen, Tianping
    IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2016, 27 (03) : 593 - 606
  • [49] Global exponential robust stability of delayed neural networks
    Li, XL
    Cao, JD
    INTERNATIONAL JOURNAL OF BIFURCATION AND CHAOS, 2004, 14 (08): : 2925 - 2931
  • [50] New results on global exponential stability of recurrent neural networks with time-varying delays
    Xu, SY
    Chu, YM
    Lu, JW
    PHYSICS LETTERS A, 2006, 352 (4-5) : 371 - 379
12345