Computing with Infinite Networks

Christopher Williams

Research output: Chapter in Book/Report/Conference proceedingConference contribution

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 paper 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 that, somewhat paradoxically, it may be easier to compute with infinite networks than finite ones.
Original languageEnglish
Title of host publicationAdvances in Neural Information Processing Systems 9
PublisherMIT Press
Pages295-301
Number of pages7
Publication statusPublished - 1997

Fingerprint

Dive into the research topics of 'Computing with Infinite Networks'. Together they form a unique fingerprint.

Cite this