Stochastic stability analysis of competitive neural networks with different time-scales

被引:22
|
作者
Meyer-Baese, Anke [1 ]
Botella, Guillermo [2 ]
Rybarska-Rusinek, Liliana [3 ]
机构
[1] Florida State Univ, Dept Comp Sci, Tallahassee, FL 32306 USA
[2] Florida State Univ, Dept Elect & Comp Engn, Tallahassee, FL 32310 USA
[3] Rzeszow Univ Technol, Dept Math, Rzeszow, Poland
关键词
Competitive neural networks; Long- and short-term memory; Stochastic stability; Singularly perturbed system; GLOBAL EXPONENTIAL STABILITY; ROBUST STABILITY; PERTURBATIONS; CRITERION; SYSTEMS; DELAY;
D O I
10.1016/j.neucom.2013.02.020
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Most computational models for competitive neural networks describe activity-connectivity interactions at different time-scales. We extend these existing models by considering stochastic processes and establish stability results based on the theory of singularly perturbed stochastic systems. Based on a reduced-order model we determine conditions that ensure the existence of the exponentially mean-square stability equilibria of the stochastic nonlinear system. It is assumed that the system is described by Ito-type equations. We derive a Lyapunov function for the coupled system and an upper bound for the parameters of the independent stochastic process. (C) 2013 Elsevier B.V. All rights reserved.
引用
收藏
页码:115 / 118
页数:4
相关论文
共 50 条
  • [1] Global exponential stability of competitive neural networks with different time-scales
    Chen, Jun
    Cui, Bao-Tong
    [J]. Xi Tong Gong Cheng Yu Dian Zi Ji Shu/Systems Engineering and Electronics, 2008, 30 (05): : 901 - 904
  • [2] Robust stability analysis of competitive neural networks with different time-scales under perturbations
    Meyer-Baese, A.
    Roberts, R.
    Yu, H. G.
    [J]. NEUROCOMPUTING, 2007, 71 (1-3) : 417 - 420
  • [3] Stability analysis for mobile robots with different time-scales based on unsupervised competitive neural networks
    Pena Fernandez, C. A.
    Cerqueira, J. J. F.
    [J]. 2017 LATIN AMERICAN ROBOTICS SYMPOSIUM (LARS) AND 2017 BRAZILIAN SYMPOSIUM ON ROBOTICS (SBR), 2017,
  • [4] Flow invariance for competitive neural networks with different time-scales
    Meyer-Bäse, A
    [J]. PROCEEDING OF THE 2002 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS, VOLS 1-3, 2002, : 858 - 861
  • [5] Local uniform stability of competitive neural networks with different time-scales under vanishing perturbations
    Meyer-Baese, A.
    Roberts, R.
    Thuemmler, V.
    [J]. NEUROCOMPUTING, 2010, 73 (4-6) : 770 - 775
  • [6] Stability of competitive neural networks with different time scales
    Wei Wu
    Baotong Cui
    [J]. DYNAMICS OF CONTINUOUS DISCRETE AND IMPULSIVE SYSTEMS-SERIES B-APPLICATIONS & ALGORITHMS, 2006, 13 : 25 - 28
  • [7] Passivity Analysis of Dynamic Neural Networks with Different Time-scales
    Wen Yu
    Xiaoou Li
    [J]. Neural Processing Letters, 2007, 25 : 143 - 155
  • [8] Some stability properties of dynamic neural networks with different time-scales
    Cruz Sandoval, Alejandro
    Yu, Wen
    Li, Xiaoou
    [J]. 2006 IEEE INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORK PROCEEDINGS, VOLS 1-10, 2006, : 4218 - +
  • [9] Passivity analysis of dynamic neural networks with different time-scales
    Sandoval, Alejandro Cruz
    Yu, Wen
    [J]. ADVANCES IN NEURAL NETWORKS - ISNN 2006, PT 1, 2006, 3971 : 86 - 92
  • [10] Passivity analysis of dynamic neural networks with different time-scales
    Yu, Wen
    Li, Xiaoou
    [J]. NEURAL PROCESSING LETTERS, 2007, 25 (02) : 143 - 155