Recurrent neural networks for solving linear matrix equations

J. Wang

Research output: Contribution to journalArticlepeer-review

50 Citations (Scopus)

Abstract

Recurrent neural networks for solving linear matrix equations are proposed. The proposed recurrent neural networks consist of two bidirectionally connected layers and each layer consists of an array of neurons. The proposed recurrent neural networks are shown to be asymptotically stable in the large and capable of computing inverse matrices and solving Lyapunov matrix equations. The operating characteristics of the proposed recurrent neural networks are demonstrated via several illustrative examples.

Original languageEnglish
Pages (from-to)23-34
Number of pages12
JournalComputers and Mathematics with Applications
Volume26
Issue number9
DOIs
Publication statusPublished - Nov 1993
Externally publishedYes

Fingerprint

Dive into the research topics of 'Recurrent neural networks for solving linear matrix equations'. Together they form a unique fingerprint.

Cite this