首页    期刊浏览 2025年07月19日 星期六
登录注册

文章基本信息

  • 标题:Convergence analysis for principal component flows
  • 本地全文:下载
  • 作者:Shintaro Yoshizawa ; Uwe Helmke ; Konstantin Starkov
  • 期刊名称:International Journal of Applied Mathematics and Computer Science
  • 电子版ISSN:2083-8492
  • 出版年度:2001
  • 卷号:11
  • 期号:1
  • 出版社:De Gruyter Open
  • 摘要:A common framework for analyzing the global convergence of several flows for principal component analysis is developed. It is shown that flows proposed by Brockett, Oja, Xu and others are all gradient flows and the global convergence of these flows to single equilibrium points is established. The signature of the Hessian at each critical point is determined
  • 关键词:principal component analysis; neural networks; gradient flows; phase portrait; Hessians
国家哲学社会科学文献中心版权所有