RECURRENT NEURAL NETWORKS FOR SOLVING SYSTEMS OF COMPLEX-VALUED LINEAR-EQUATIONS

被引：14

作者：

WANG, J

机构：

[1] Department of Industrial Technology, University of North Dakota, Grand Forks

来源：

ELECTRONICS LETTERS | 1992年 / 28卷 / 18期

关键词：

NEURAL NETWORKS; MATRIX ALGEBRA;

D O I：

10.1049/el:19921115

中图分类号：

TM [电工技术]; TN [电子技术、通信技术];

学科分类号：

0808 ; 0809 ;

摘要：

Recurrent neural networks are presented for solving systems of linear equations involving complex-valued coefficients. The recurrent neural networks are shown to be able to generate unknown solutions of complex-valued linear equations. The configurations of the recurrent neural networks are described. An example is also discussed.

引用

页码：1751 / 1753

页数：3