A Recurrent Neural Network for Extreme Eigenvalue Problem

Abstract

This paper presents a novel recurrent time continuous neural network model for solving eigenvalue and eigenvector problem. The network is proved to be globally convergent to an exact eigenvector of a matrix A with respect to the problem’s feasible region. This convergence is called quasi-convergence in the sense of the starting point to be in the feasible… (More)
DOI: 10.1007/11538059_82

5 Figures and Tables

Topics

  • Presentations referencing similar topics