摘要
针对一类能够由中立型变延迟非线性微分方程描述的神经网络模型,给出了全局渐近稳定的不依赖于时间延迟的充分条件.所得到的稳定判据不仅考虑了神经元的激励和抑制对网络的影响,而且易于验证.仿真示例验证了所得结论的有效性.
A sufficient condition guaranteeing the global asymptotical stability of the equilibrium point is derived for a class of neural network models with variable delay and neutral type delay. The stability criterion not only eliminates the differences between excitatory and inhibitory effects on the neural networks, but also can be conveniently checked. Numerical example shows the effectiveness of the obtained results.
出处
《控制与决策》
EI
CSCD
北大核心
2006年第5期527-531,535,共6页
Control and Decision
基金
国家自然科学基金项目(60244017
60325311)
辽宁省自然科学基金项目(20022030)
关键词
延迟神经网络
中立型
全局渐近稳定
线性矩阵不等式
时变延迟
Delayed neural networks
Neutral type
Global asymptotical stability
Linear matrix inequality (LMI)
Time varying delay