Recurrent neural networks for solving systems of complex-valued linear equations

Research output: Journal Publications and ReviewsRGC 21 - Publication in refereed journalpeer-review

17 Scopus Citations
View graph of relations



Original languageEnglish
Pages (from-to)1751-1753
Journal / PublicationElectronics Letters
Issue number18
Publication statusPublished - 1 Jan 1992
Externally publishedYes


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.