Computing with infinite networks

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.

Divisions: Aston University (General)
Additional Information: Copyright of the Massachusetts Institute of Technology Press (MIT Press)
Event Title: 10th Annual Conference on Neural Information Processing Systems, NIPS 1996
Event Type: Other
Event Dates: 1996-12-02 - 1996-12-05
Uncontrolled Keywords: neural networks,weight-priors,Gaussian process,sigmoidal,Computer Networks and Communications,Information Systems,Signal Processing
ISBN: 0262100657
Full Text Link:
Related URLs: http://www.scop ... tnerID=8YFLogxK (Scopus URL)
http://mitpress ... type=2&tid=3990 (Publisher URL)
PURE Output Type: Conference contribution
Published Date: 1996
Authors: Williams, Christopher K. I.

Download

[img]

Version: Published Version


Export / Share Citation


Statistics

Additional statistics for this record