Recurrent neural networks for computing pseudoinverses of rank-deficient matrices

Jun Wang

Research output: Contribution to journalArticlepeer-review

107 Citations (Scopus)

Abstract

Three recurrent neural networks are presented for computing the pseudoinverses of rank-deficient matrices. The first recurrent neural network has the dynamical equation similar to the one proposed earlier for matrix inversion and is capable of Moore-Penrose inversion under the condition of zero initial states. The second recurrent neural network consists of an array of neurons corresponding to a pseudoinverse matrix with decaying self-connections and constant connections in each row or column. The third recurrent neural network consists of two layers of neuron arrays corresponding, respectively, to a pseudoinverse matrix and a Lagrangian matrix with constant connections. All three recurrent neural networks are also composed of a number of independent subnetworks corresponding to the rows or columns of a pseudoinverse. The proposed recurrent neural networks are shown to be capable of computing the pseudoinverses of rank-deficient matrices.

Original languageEnglish
Pages (from-to)1479-1493
Number of pages15
JournalSIAM Journal of Scientific Computing
Volume18
Issue number5
DOIs
Publication statusPublished - Sep 1997
Externally publishedYes

Keywords

  • Dynamical systems
  • Generalized inverses
  • Neural networks

Fingerprint

Dive into the research topics of 'Recurrent neural networks for computing pseudoinverses of rank-deficient matrices'. Together they form a unique fingerprint.

Cite this