Title :
Global stability analysis in dynamical neural networks with distributed time delays
Author :
Zhang, Jiye ; Jin, Xuesong ; Zhang, Weihua
Author_Institution :
Nat. Traction Power Lab., Southwest Jiaotong Univ., Chengdu, China
fDate :
29 June-1 July 2002
Abstract :
In this paper, without assuming the boundedness and differentiability of the activation functions, the conditions ensuring existence, uniqueness, and global asymptotical stability of the equilibrium point of neural networks with distributed time delays and variable delays are studied. By constructing proper nonlinear integro-differential inequalities involving both variable delays and unbounded delay and using M-matrix. theory, the sufficient conditions for global asymptotic stability are obtained.
Keywords :
asymptotic stability; delays; integro-differential equations; neural nets; M-matrix. theory; asymptotical stability; distributed time delays; dynamical neural networks; equilibrium point; existence; global stability analysis; nonlinear integro-differential inequalities; unbounded delay; uniqueness; variable delays; Asymptotic stability; Delay effects; Delay systems; Integrodifferential equations; Intelligent networks; Laboratories; Neural networks; Neurons; Signal processing; Stability analysis;
Conference_Titel :
Communications, Circuits and Systems and West Sino Expositions, IEEE 2002 International Conference on
Print_ISBN :
0-7803-7547-5
DOI :
10.1109/ICCCAS.2002.1179096
