IEEE Trans Cybern. 2014 Dec;44(12):2848-60. doi: 10.1109/TCYB.2014.2317236. Epub 2014 Apr 23.
In this paper, the problem of adaptive synchronization is investigated for stochastic neural networks of neutral-type with Markovian switching parameters. Using the M-matrix approach and the stochastic analysis method, some sufficient conditions are obtained to ensure three kinds of adaptive synchronization for the stochastic neutral-type neural networks. These three kinds of adaptive synchronization include the almost sure asymptotical synchronization, exponential synchronization in p th moment and almost sure exponential synchronization. Some numerical examples are provided to illustrate the effectiveness and potential of the proposed design techniques.
本文研究了具有马尔可夫切换参数的中立型随机神经网络的自适应同步问题。利用 M-矩阵方法和随机分析方法，得到了保证随机中立型神经网络三种自适应同步的充分条件。这三种自适应同步包括几乎必然渐近同步、p 阶矩指数同步和几乎必然指数同步。通过数值例子说明了所提出的设计技术的有效性和潜力。
