Nonlinearly Activated Recurrent Neural Network for Computing the Drazin Inverse
Nonlinearly Activated Recurrent Neural Network for Computing the Drazin Inverse
复制标题
用于计算 Drazin 逆的非线性激活循环神经网络
DOI:
10.1007/s11063-017-9581-y
复制
发表时间:
2017-01
影响因子:
3.1
通讯作者:
Stanimirovic Predrag S.
中科院分区:
文献类型:
--
作者:
Wang Xuezhong;Ma Haifeng;Stanimirovic Predrag S.
Four gradient-based recurrent neural networks for computing the Drazin inverse of a square real matrix are developed. Theoretical analysis shows that any monotonically-increasing odd activation function ensures the global convergence performance of defined neural network models. The computer simulation results further substantiate that the considered neural networks could compute the Drazin inverse with accuracy and effectiveness. Moreover, the presented neural networks show superior convergence in the case when the power-sigmoid activation functions are used compared to linear models.
登录
查看更多内容
DOI:
10.2307/3614217
发表时间:
1968-10
期刊:
The Mathematical Gazette
影响因子:
--
作者:
F. Smithies;I. G. Petrovski;Richard A. Silverman
通讯作者:
F. Smithies;I. G. Petrovski;Richard A. Silverman
DOI:
10.1007/0-8176-4435-0
发表时间:
2010-08
期刊:
--
影响因子:
--
作者:
P. Antsaklis;Anthony N. Michel
通讯作者:
P. Antsaklis;Anthony N. Michel
DOI:
10.1002/9780470226773.ch22
发表时间:
1999-06
期刊:
Applied Numerical Methods Using Matlab®
影响因子:
--
作者:
Bernd S. W. Schröder
通讯作者:
Bernd S. W. Schröder
DOI:
10.1109/tcsi.2008.2007065
发表时间:
2009-07
期刊:
IEEE Transactions on Circuits and Systems I: Regular Papers
影响因子:
--
作者:
Yunong Zhang;Weimu Ma;Binghuang Cai
通讯作者:
Yunong Zhang;Weimu Ma;Binghuang Cai
DOI:
10.1016/s0096-3003(99)00252-0
发表时间:
2001-04
期刊:
Appl. Math. Comput.
影响因子:
--
作者:
Yong-Lin Chen
通讯作者:
Yong-Lin Chen