摘要
针对非自治的动态神经网络系统,建立了动态神经网络的数学模型,并将其等效成一个非线性仿射控制系统.深入分析了该系统平衡点的存在性、唯一性和全局渐近稳定性,给出了系统输入-状态稳定的充分条件,构建了ISS-Lyapunov函数,并应用该函数确保了系统的全局渐近稳定性.
A mathematical model of dynamic neural networks is built, which is shown to be equivalent to an affine nonlinear control system. The existence and uniqueness of the equilibrium point and the global stability of dynamic neural network models for the non-autonomous case are investigated. The sufficient conditions for the input-to-state stability are provided. ISS-Lyapunov functions are constructed and employed to insure global asymptotic stability of systems.
出处
《控制与决策》
EI
CSCD
北大核心
2004年第12期1391-1394,共4页
Control and Decision
关键词
动态神经网络
全局渐近稳定性
输入-状态稳定性
Mathematical models
Nonlinear systems
System stability
Theorem proving
Transfer functions