A Numerical Study on Learning Curves in Stochastic Multilayer Feedforward Networks

K. R. Müller, M. Finke, N. Murata, K. Schulten, S. Amari

研究成果: Article査読

29 被引用数 (Scopus)

抄録

The universal asymptotic scaling laws proposed by Amari et al. are studied in large scale simulations using a CM5. Small stochastic multilayer feedforward networks trained with backpropagation are investigated. In the range of a large number of training patterns t, the asymptotic generalization error scales as 1/t as predicted. For a medium range t a faster 1/t2 scaling is observed. This effect is explained by using higher order corrections of the likelihood expansion. It is shown for small t that the scaling law changes drastically, when the network undergoes a transition from strong overfitting to effective learning.

本文言語English
ページ(範囲)1085-1106
ページ数22
ジャーナルNeural Computation
8
5
DOI
出版ステータスPublished - 1996 7 1
外部発表はい

ASJC Scopus subject areas

  • Arts and Humanities (miscellaneous)
  • Cognitive Neuroscience

フィンガープリント 「A Numerical Study on Learning Curves in Stochastic Multilayer Feedforward Networks」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