共 55 条
Finite-Time Stability for Delayed Complex-Valued BAM Neural Networks
被引:31
作者:
Zhang, Ziye
[1
]
Liu, Xiaoping
[2
]
Guo, Runan
[1
]
Lin, Chong
[3
]
机构:
[1] Shandong Univ Sci & Technol, Coll Math & Syst Sci, Qingdao 266590, Peoples R China
[2] Lakehead Univ, Dept Elect Engn, Thunder Bay, ON P7B 5E1, Canada
[3] Qingdao Univ, Inst Complex Sci, Qingdao 266071, Peoples R China
基金:
加拿大自然科学与工程研究理事会;
中国国家自然科学基金;
关键词:
Finite-time stability;
Complex-valued BAM neural networks;
Time delay;
BIDIRECTIONAL ASSOCIATIVE MEMORIES;
LIPSCHITZ NONLINEAR-SYSTEMS;
VARYING DELAYS;
GLOBAL STABILITY;
DISCONTINUOUS ACTIVATIONS;
EXPONENTIAL STABILITY;
MISSING MEASUREMENTS;
PERIODIC-SOLUTION;
HOPF-BIFURCATION;
SYNCHRONIZATION;
D O I:
10.1007/s11063-017-9710-7
中图分类号:
TP18 [人工智能理论];
学科分类号:
081104 ;
0812 ;
0835 ;
1405 ;
摘要:
This paper studies the finite-time stability problem of complex-valued BAM neural networks with time delay. Firstly, based on a more suitable assumption for the complex-valued activation functions of the considered system, a tractable entire real-valued system is formed. Using nonlinear measure approach, a condition to ensure the existence and uniqueness of the equilibrium point for this system is derived. Then, a finite-time stability criterion of the equilibrium point is obtained in terms of LMIs by Lyapunov function approach. In the end, simulation examples are provided to verify the validity and advantages of the proposed conditions.
引用
收藏
页码:179 / 193
页数:15
相关论文