温州大学学报(自然科学版)
溫州大學學報(自然科學版)
온주대학학보(자연과학판)
JOURNAL OF WENZHOU UNIVERSITY(NATURAL SCIENCES)
2014年
3期
1-11
,共11页
耦合神经网络系统%离散时间系统%混合时滞%同步%鲁棒
耦閤神經網絡繫統%離散時間繫統%混閤時滯%同步%魯棒
우합신경망락계통%리산시간계통%혼합시체%동보%로봉
Coupled Neural Networks Systems%Discrete-time Systems%Mixed Time Delays%Synchronization%Robust
讨论了一类离散时间的时滞耦合神经网络的同步问题。在参数不确定的离散时间耦合神经网络中,考虑了变时滞和有限分布时滞。同时,细胞激活函数假设为较Lipschitz条件更为一般的扇形非线性函数,该函数可以既不可微又不严格单调。通过构造Lyapunov-Krasovskii泛函,运用线性矩阵不等式(LMI)技术,并结合Kronecker积来获得耦合神经网络鲁棒全局指数同步的充分性判据,并且所获得的判据依赖于时滞。最后,对一个实例进行仿真,说明结论的有效性。
討論瞭一類離散時間的時滯耦閤神經網絡的同步問題。在參數不確定的離散時間耦閤神經網絡中,攷慮瞭變時滯和有限分佈時滯。同時,細胞激活函數假設為較Lipschitz條件更為一般的扇形非線性函數,該函數可以既不可微又不嚴格單調。通過構造Lyapunov-Krasovskii汎函,運用線性矩陣不等式(LMI)技術,併結閤Kronecker積來穫得耦閤神經網絡魯棒全跼指數同步的充分性判據,併且所穫得的判據依賴于時滯。最後,對一箇實例進行倣真,說明結論的有效性。
토론료일류리산시간적시체우합신경망락적동보문제。재삼수불학정적리산시간우합신경망락중,고필료변시체화유한분포시체。동시,세포격활함수가설위교Lipschitz조건경위일반적선형비선성함수,해함수가이기불가미우불엄격단조。통과구조Lyapunov-Krasovskii범함,운용선성구진불등식(LMI)기술,병결합Kronecker적래획득우합신경망락로봉전국지수동보적충분성판거,병차소획득적판거의뢰우시체。최후,대일개실례진행방진,설명결론적유효성。
This paper addresses the analysis problem of synchronization for a class of discrete-time coupled neural networks with time-varying and distributed delays. The neural networks are subject to parameter uncertainty. Furthermore, the description of the activation functions is a more general sector nonlinear function than the recently commonly-used Lipschitz conditions, which are assumed to be neither differentiable nor strictly monotonic. By referring to Lyapunov functional method and Kronecker product technique, some sufficient conditions depending on delay are derived for robust exponential synchronization of such systems. Finally, a simulation example is presented to show the usefulness of the derived LMI-based synchronization scheme.