Edinburgh Research Explorer

Computation With Infinite Neural Networks

Research output: Contribution to journalArticle

Original languageEnglish
Pages (from-to)1203-1216
Number of pages14
JournalNeural Computation
Volume10
Issue number5
DOIs
Publication statusPublished - 1 Jul 1997

Abstract

For neural networks with a wide class of weight priors, it can be shown that in the limit of an infinite number of hidden units, the prior over functions tends to a gaussian process. In this article, analytic forms are derived for the covariance function of the gaussian processes corresponding to networks with sigmoidal and gaussian hidden units. This allows predictions to be made efficiently using networks with an infinite number of hidden units and shows, somewhat paradoxically, that it may be easier to carry out Bayesian prediction with infinite networks rather than finite ones.

ID: 24656427