Novel Superlinear First Order Algorithms(Neural Networks and Bioengineering)

スポンサーリンク

概要

• 論文の詳細を見る

• Applying the formerly proposed classification framework for first order line search optimization techniques [1] we introduce novel superlinear first order line search methods. Novelty of the methods lies in the line search subproblem. The presented line search subproblem features automatic step length and momentum adjustments at every iteration of the algorithms realizable in a single step calculation. This keeps the computational complexity of the algorithms linear and does not harm the stability and convergence of the methods. The algorithms have none or linear memory requirements and are shown to be convergent and capable of reaching the superlinear convergence rates. They were practically applied to artificial neural network training and compared to the relevant training methods within the same class. The simulation results show satisfactory performance of the introduced algorithms over the standard and previously proposed methods.

• 社団法人電子情報通信学会の論文
• 2004-06-01

著者

• Usui Shiro

  Riken Bsi

• GECZY Peter

  RIKEN BSI

• Usui Shiro

  Riken Brain Science Institute

関連論文

• Novel Superlinear First Order Algorithms(Neural Networks and Bioengineering)
• ON LAWRENCE STARK AND BIOMEDICAL ENGINEERING

スポンサーリンク