CAJ | 학술논문

利用非负鞅收敛定理、Lyapunov 泛函方法和网络自身的特性讨论了变时滞随机递归神经网络的随机指数稳定性,给出了这类神经网络随机指数稳定性的新的代数准则,所给代数准则简单易用.两个应用实例说明即使针对随机Hopfield 神经网络所给的代数准则也优于相关的判别准则.
이용비부앙수렴정리、Lyapunov 범함방법화망락자신적특성토론료변시체수궤체귀신경망락적수궤지수은정성,급출료저류신경망락수궤지수은정성적신적대수준칙,소급대수준칙간단역용.량개응용실례설명즉사침대수궤Hopfield 신경망락소급적대수준칙야우우상관적판별준칙.
The almost exponential stability for a stochastic recurrent neural network with time-varying delays is discussed by means of a nonnegative semi-martingale convergence theorem, the Lyapunov functional method and the characteristics of stochastic delay recurrent neural networks. The new algebraic criteria of the almost exponential stability for the stochastic recurrent neural network with time-varying delays is derived. These algebraic criteria are simple and practical. Two examples show these new algebraic criteria are better than the relative criteria for the stochastic Hopfield neural network.