Delay-dependent robust dissipativity conditions for delayed neural networks with random uncertainties
Delay-dependent robust dissipativity conditions for delayed neural networks with random uncertainties
复制标题
DOI：
10.1016/j.amc.2013.07.017
复制
发表时间：
2013-09
期刊：
影响因子：
--
通讯作者：
Junchang Wang;Ju H. Park;Hao Shen;Jian Wang
中科院分区：
文献类型：
--
作者：
Junchang Wang;Ju H. Park;Hao Shen;Jian Wang
研究了具有随机不确定性的时滞神经网络的鲁棒耗散分析问题。所考虑的随机不确定性假设遵循某些相互不相关的伯努利分布白噪声序列。利用互凸方法结合广义Wirtinger不等式，建立了相关神经网络随机严格（Q， S， R）-θ-耗散的延迟相关条件。最后，给出了两个数值算例，说明了该方法的保守性降低和有效性。
This paper deals with the problem of the robust dissipativity analysis for delayed neural networks with randomly occurring uncertainties. The randomly occurring uncertainties under consideration are assumed to follow certain mutually uncorrelated Bernoulli distributed white noise sequences. By using reciprocally convex approach combined with an extended Wirtinger inequality, some delay-dependent conditions for the concerned neural networks to be stochastically strictly (Q, S, R)-θ-dissipative are established. Finally, two numerical examples are given to illustrate the reduced conservatism and effectiveness of our proposed approach.