Slow dynamics due to singularities of hierarchical learning machines

Hyeyoung Park, Masato Inoue, Masato Okada

研究成果: Article

10 引用 (Scopus)

抜粋

Recently, slow dynamics in learning of neural networks has been known to be closely related to singularities, which exist in parameter spaces of hierarchical learning models. To show the influence of singular structure on learning dynamics, we take statistical mechanical approaches and investigate online-learning dynamics under various learning scenario with different relationship between optimum and singularities. From the investigation, we found a quasi-plateau phenomenon which differs from the well known plateau. The quasi-plateau and plateau become extremely serious when an optimal point is in a neighborhood of a singularity. The quasi-plateau and plateau disappear in the natural gradient learning, which takes singular structures into account and uses Riemannian measure for the parameter space.

元の言語English
ページ(範囲)275-279
ページ数5
ジャーナルProgress of Theoretical Physics Supplement
157
DOI
出版物ステータスPublished - 2005 1 1

ASJC Scopus subject areas

  • Physics and Astronomy (miscellaneous)

フィンガープリント Slow dynamics due to singularities of hierarchical learning 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