Exponential state estimation for recurrent neural networks with distributed delays

Exponential state estimation for recurrent neural networks with distributed delays
复制标题

具有分布式延迟的循环神经网络的指数状态估计

DOI:
10.1016/j.neucom.2007.07.005
复制
发表时间:
2007-12
期刊:
影响因子:
6
通讯作者:
Fei, Shu-Min
Fei, Shu-Min
中科院分区:
计算机科学2区
文献类型:
--
作者:
Li, Tao;Fei, Shu-Min

文献摘要

参考文献

被引文献

相似文献

本文研究了同时具有时变时滞和分布时变时滞的递归神经网络的时滞相关状态估计问题。通过可用的输出测量,建立了一个依赖于延迟的准则来估计神经元状态,使得估计误差的动态是全局指数稳定的。时变时滞的导数满足τ stec(t)<$μ,激励函数既不是单调的也不是可微的,比最近常用的Lipschitz条件更一般.最后,给出了两个说明性的例子来证明所得到的条件的有用性。
In this paper, the delay-dependent state estimation problem for recurrent neural networks with both time-varying and distributed time-varying delays is investigated. Through available output measurements, a delay-dependent criterion is established to estimate the neuron states such that the dynamics of the estimation error is globally exponentially stable. The derivative of a time-varying delay satisfies τ˙(t)⩽μ and the activation functions are assumed to be neither monotonic nor differentiable, and more general than the recently commonly used Lipschitz conditions. Finally, two illustrative examples are given to demonstrate the usefulness of the obtained condition.
DOI: 10.1016/j.neunet.2003.08.007
发表时间: 2004-04
期刊: Neural networks : the official journal of the International Neural Network Society
影响因子: --
作者:
Jinde Cao;Jun Wang
通讯作者: Jinde Cao;Jun Wang
DOI: 10.1109/tnn.2006.881488
发表时间: 2006-11
影响因子: --
作者:
Jinde Cao;Kun Yuan;Han-Xiong Li
通讯作者: Jinde Cao;Kun Yuan;Han-Xiong Li
DOI: 10.1016/j.physleta.2005.05.016
发表时间: 2005-07
期刊: Physics Letters A
影响因子: 2.6
作者:
Shengyuan Xu;J. Lam;D. Ho
通讯作者: Shengyuan Xu;J. Lam;D. Ho
DOI: 10.1016/j.chaos.2005.08.183
发表时间: 2006-12
影响因子: 7.8
作者:
Vimal Singh
通讯作者: Vimal Singh
DOI: 10.1109/tcsi.2004.841574
发表时间: 2005-02-01
影响因子: 5.1
作者:
Cao, JD;Wang, J
通讯作者: Wang, J