Noise-Induced Stabilization of the Recurrent Neural Networks With Mixed Time-Varying Delays and Markovian-Switching Parameters
Noise-Induced Stabilization of the Recurrent Neural Networks With Mixed Time-Varying Delays and Markovian-Switching Parameters
复制标题
DOI：
10.1109/tnn.2007.903159
复制
发表时间：
2007-11
影响因子：
--
通讯作者：
Yi Shen;Jun Wang
中科院分区：
文献类型：
--
作者：
Yi Shen;Jun Wang
讨论了具有混合时变时滞和马尔可夫切换参数的递归神经网络的噪声镇定问题。首先，在噪声存在的情况下，给出了具有混合时变时滞和马尔可夫切换参数的递归神经网络（NN）的唯一状态的存在性的一个新结果，而不需要满足一般随机马尔可夫切换系统所要求的线性增长条件.其次，利用有限差分公式、Gronwall不等式、大数定律和马尔可夫链的遍历性，得到了相关递归神经网络的时滞依赖稳定性条件。结果表明，总存在一个合适的白色噪声，使得任何具有混合时变时滞和马尔可夫切换参数的常返神经网络，只要时滞足够小，都能被噪声指数镇定.
The stabilization of recurrent neural networks with mixed time-varying delays and Markovian-switching parameters by noise is discussed. First, a new result is given for the existence of unique states of recurrent neural networks (NNs) with mixed time-varying delays and Markovian-switching parameters in the presence of noise, without the need to satisfy the linear growth conditions required by general stochastic Markovian-switching systems. Next, a delay-dependent condition for stabilization of concerned recurrent NNs is derived by applying the ltd formula, the Gronwall inequality, the law of large numbers, and the ergodic property of Markovian chain. The results show that there always exists an appropriate white noise such that any recurrent NNs with mixed time-varying delays and Markovian-switching parameters can be exponentially stabilized by noise if the delays are sufficiently small.