A Numerical Study on Learning Curves in Stochastic Multilayer Feedforward Networks

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

Research output: Contribution to journalArticlepeer-review

Abstract

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.

Original languageEnglish (US)
Pages (from-to)1085-1106
Number of pages22
JournalNeural Computation
Volume8
Issue number5
DOIs
StatePublished - Jul 1 1996

ASJC Scopus subject areas

  • Arts and Humanities (miscellaneous)
  • Cognitive Neuroscience

Fingerprint

Dive into the research topics of 'A Numerical Study on Learning Curves in Stochastic Multilayer Feedforward Networks'. Together they form a unique fingerprint.

Cite this