Dynamics of the adaptive natural gradient descent method for soft committee machines

Masato Inoue, Hyeyoung Park, Masato Okada

研究成果: Article

4 引用 (Scopus)

抜粋

The learning efficiency of a simplified version of adaptive natural gradient descent (ANGD) for soft committee machines was evaluated. Statistical-mechanical techniques, which extract order parameters and make the stochastic learning dynamics converge towards deterministic at the large limit of the input dimension N [1,2], were employed. ANGD was found to perform as well as natural gradient descent (NGD). The key condition affecting the learning plateau in ANGD were also revealed.

元の言語English
記事番号056120
ページ(範囲)056120-1-056120-14
ジャーナルPhysical Review E - Statistical, Nonlinear, and Soft Matter Physics
69
発行部数5 1
出版物ステータスPublished - 2004 5 1
外部発表Yes

ASJC Scopus subject areas

  • Statistical and Nonlinear Physics
  • Statistics and Probability
  • Condensed Matter Physics

フィンガープリント Dynamics of the adaptive natural gradient descent method for soft committee machines' の研究トピックを掘り下げます。これらはともに一意のフィンガープリントを構成します。

  • これを引用