Network Information Criterion—Determining the Number of Hidden Units for an Artificial Neural Network Model

Noboru Murata, Shuji Yoshizawa, Shun Ichi Amari

研究成果: Article査読

415 被引用数 (Scopus)

抄録

The problem of model selection, or determination of the number of hidden units, can be approached statistically, by generalizing Akaike’s information criterion (AIC) to be applicable to unfaithful (i.e., unrealizable) models with general loss criteria including regularization terms. The relation between the training error and the generalization error is studied in terms of the number of the training examples and the complexity of a network which reduces to the number of parameters in the ordinary statistical theory of the AIC. This relation leads to a new Network Information Criterion (NIC) which is useful for selecting the optimal network model based on a given training set.

本文言語English
ページ(範囲)865-872
ページ数8
ジャーナルIEEE Transactions on Neural Networks
5
6
DOI
出版ステータスPublished - 1994 11
外部発表はい

ASJC Scopus subject areas

  • Software
  • Computer Science Applications
  • Computer Networks and Communications
  • Artificial Intelligence

フィンガープリント 「Network Information Criterion—Determining the Number of Hidden Units for an Artificial Neural Network Model」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