Statistical analysis of learning dynamics

Noboru Murata, Shun Ichi Amari

研究成果: Article査読

27 被引用数 (Scopus)

抄録

Learning is a flexible and effective means of extracting the stochastic structure of the environment. It provides an effective method for blind separation and deconvolution in signal processing. Two different types of learning are used, namely batch learning and on-line learning. The batch learning procedure uses all the training examples repeatedly so that its performance is compared to the statistical estimation procedure. On-line learning is more dynamical, updating the current estimate by observing a new datum one by one. On-line learning is slow in general but works well in the changing environment. The present paper gives a unified framework of statistical analysis for batch and on-line learning. The topics include the asymptotic learning curve, generalization error and training error, over-fitting and over-training, efficiency of learning, and an adaptive method of determining learning rate.

本文言語English
ページ(範囲)3-28
ページ数26
ジャーナルSignal Processing
74
1
DOI
出版ステータスPublished - 1999 4月
外部発表はい

ASJC Scopus subject areas

  • 制御およびシステム工学
  • ソフトウェア
  • 信号処理
  • コンピュータ ビジョンおよびパターン認識
  • 電子工学および電気工学

フィンガープリント

「Statistical analysis of learning dynamics」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル