摘要
研究一类Hopfield神经网络系统的平衡状态的存在性、唯一性与全局稳定性 ,这类系统放弃了以前对激励函数的有界性、单调性和可微性要求 .利用M矩阵理论 ,通过构造适当的Lyapunov函数 ,得到了系统全局渐近稳定的充分条件 .
The existence and uniqueness of the equilibrium and the global attractivity of Hopfield neural network models are investigated. Instead of assuming the boundedness, monotonicity and differentiability of the activation functions and by using M matrix theory, Lyapunov functions are constructed and employed to establish sufficient conditions for global asymptotic stability.
出处
《控制理论与应用》
EI
CAS
CSCD
北大核心
2003年第2期180-184,共5页
Control Theory & Applications
基金
supportedbytheNationalNaturalScienceFoundationofChina( 10 2 72 0 91)
theNaturalScienceFoundationofSouthwestJiaotongUniversi ty ( 2 0 0 1B0 9)
