Cycle-symmetric matrices and convergent neural networks

Research output: Contribution to journalArticlepeer-review

13 Scopus citations

Abstract

This work investigates a class of neural networks with cycle-symmetric connection strength. We shall show that, by changing the coordinates, the convergence of dynamics by Fiedler and Gedeon is equivalent to the classical results. This presentation also addresses the extension of the convergence theorem to other classes of signal functions with saturations. In particular, the result of Cohen and Grossberg is recast and extended with a more concise verification.

Original languageEnglish
Pages (from-to)213-220
Number of pages8
JournalPhysica D: Nonlinear Phenomena
Volume146
Issue number1-4
DOIs
StatePublished - 15 Nov 2000

Keywords

  • Neural networks
  • Cycle-symmetric matrix
  • Lyapunov function
  • Convergence of dynamics

Fingerprint

Dive into the research topics of 'Cycle-symmetric matrices and convergent neural networks'. Together they form a unique fingerprint.

Cite this