CAJ | 학술논문

本文研究了Cohen Grossberg神经网络模型的指数稳定性.为避免构造Lyapunov函数的困难,我们采用广义相对Dalquist数方法来分析神经网络的稳定性.借助这一方法,我们不但得到了Cohen-Grossberg神经网络模型平衡解的存在性、唯一性和全局指数稳定性的新的充分条件,而且给出了神经网络的指数衰减估计.所获结论改进了已有文献的相关结果.
본문연구료Cohen Grossberg신경망락모형적지수은정성.위피면구조Lyapunov함수적곤난,아문채용엄의상대Dalquist수방법래분석신경망락적은정성.차조저일방법,아문불단득도료Cohen-Grossberg신경망락모형평형해적존재성、유일성화전국지수은정성적신적충분조건,이차급출료신경망락적지수쇠감고계.소획결론개진료이유문헌적상관결과.
In this paper,the exponential stability of Cohen-Grossberg neural network model is considered. To avoid the difficulty of constructing a proper Lyapunov function, the generalized relative Dahlquist constant approach is employed to analyze the stability of neural networks, and sufficient conditions for the existence of a unique equilibrium and the global exponential stability of CohenGrossberg neural networks are presented. Moreover,the exponential convergence rate of the neural networks to stable equilibrium point is estimated. Our results improve the existing ones.