作者: Jigui Jian , Baoxian Wang
DOI: 10.1016/J.NEUCOM.2014.07.041
关键词:
摘要: In this paper, Lagrange stability for a class of neutral type BAM neural networks with multiple time-varying and bounded or unbounded delays is studied. Various different types activation functions are considered, including general functions. By constructing appropriate Lyapunov applying inequality techniques, some easily verifiable algebraic criteria the ultimate boundedness globally attractive sets obtained. Meanwhile, estimations positive invariant set, set exponentially given. particular, respect to partial variables systems derived. These results here generalize improve earlier publications can be applied monostable multistable as well chaos control synchronization. Finally, examples numerical simulations also given demonstrate our results. HighlightsWe discuss networks.We give detailed sets.The multi-time-varying but not distributed delays.The publications.The two sufficient conditions poly-stability in sense