Stability analysis of fractional-order Hopfield neural networks with discontinuous activation functions

Stability analysis of fractional-order Hopfield neural networks with discontinuous activation functions
复制标题

具有不连续激活函数的分数阶 Hopfield 神经网络的稳定性分析

DOI:
10.1016/j.neucom.2015.07.077
复制
发表时间:
2016
期刊:
影响因子:
6
通讯作者:
Wang Qing
Wang Qing
中科院分区:
计算机科学2区
文献类型:
--
作者:
Zhang Shuo;Yu Yongguang;Wang Qing

文献摘要

参考文献

被引文献

相似文献

分数阶 Hopfield 神经网络通常用于模拟神经元相互作用的信息处理。对于一类具有不连续激活函数的网络,需要研究其解的存在性和稳定性条件。在Filippov解的框架下,首先给出增长条件来保证其解的存在性。然后,利用李亚普诺夫泛函提出了此类不连续网络解的有界性和稳定性的一些充分条件。最后通过数值算例验证了理论结果的有效性。
Fractional-order Hopfield neural networks are often used to model the information processing of neuronal interactions. For a class of such networks with discontinuous activation functions, it is needed to investigate the existence and stability conditions of their solutions. Under the framework of Filippov solutions, a growth condition is firstly given to guarantee the existence of their solutions. Then, some sufficient conditions are proposed for the boundedness and stability of the solutions of such discontinuous networks by employing the Lyapunov functionals. Finally, a numerical example is presented to demonstrate the effectiveness of the theoretical results.
DOI: 10.1088/1751-8113/43/8/085002
发表时间: 2010-02
期刊: Journal of Physics A: Mathematical and Theoretical
影响因子: --
作者:
G. Cottone;M. Paola;R. Santoro
通讯作者: G. Cottone;M. Paola;R. Santoro
DOI: 10.1109/tcsi.2003.818614
发表时间: 2003-11
影响因子: 5.1
作者:
M. Forti;P. Nistri
通讯作者: M. Forti;P. Nistri
DOI: 10.1038/nn.2212
发表时间: 2008-11
影响因子: 25
作者:
Lundstrom, Brian N.;Higgs, Matthew H.;Spain, William J.;Fairhall, Adrienne L.
通讯作者: Fairhall, Adrienne L.
DOI: 10.1016/j.amc.2007.12.029
发表时间: 2008-07
期刊: Appl. Math. Comput.
影响因子: --
作者:
Yongqing Yang;Jinde Cao
通讯作者: Yongqing Yang;Jinde Cao
DOI: 10.1016/j.neucom.2013.02.021
发表时间: 2013-10
期刊: Neurocomputing
影响因子: 6
作者:
Jian Xiao;Z. Zeng;Wenwen Shen
通讯作者: Jian Xiao;Z. Zeng;Wenwen Shen