Mean-square exponential input-to-state stability of stochastic fuzzy delayed Cohen-Grossberg neural networks

We consider a class of stochastic fuzzy delayed Cohen-Grossberg neural networks without global Lipschitz condition. Based on local Lipschitz condition, we prove the solutions of the given neural networks exist globally and are mean-square exponentially input-to-state stable. Moreover, we highlight the advantages of our novel results by comparing with the results in Zhu and Li (2012) as well as a numerical example.

本文研究一类不满足全局Lipschitz条件（global Lipschitz condition）的随机模糊时滞Cohen-Grossberg神经网络（stochastic fuzzy delayed Cohen-Grossberg neural networks）。基于局部Lipschitz条件（local Lipschitz condition），本文证明了所研究神经网络的解全局存在且具备均方指数输入到状态稳定性（mean-square exponentially input-to-state stable）。此外，通过与Zhu和Li（2012）的研究结果对比，并结合数值算例，本文进一步凸显了所获新颖结论的优势。