Issues in Bayesian Analysis of Neural Network Models

Stemming from work by Buntine and Weigend (1991) and MacKay (1992), there is a growing interest in Bayesian analysis of neural network models. Although conceptually simple, this problem is computationally involved. We suggest a very efficient Markov chain Monte Carlo scheme for inference and predict...

Full description

Saved in:
Bibliographic Details
Published in:Neural computation 1998-04, Vol.10 (3), p.749-770
Main Authors: Müller, Peter, Insua, David Rios
Format: Article
Language:English
Subjects:
Applied sciences
Artificial intelligence
Computer science
control theory
systems
Connectionism. Neural networks
Exact sciences and technology
Simulation
Software
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Stemming from work by Buntine and Weigend (1991) and MacKay (1992), there is a growing interest in Bayesian analysis of neural network models. Although conceptually simple, this problem is computationally involved. We suggest a very efficient Markov chain Monte Carlo scheme for inference and prediction with fixed-architecture feedforward neural networks. The scheme is then extended to the variable architecture case, providing a data-driven procedure to identify sensible architectures.
ISSN:0899-7667
1530-888X
DOI:10.1162/089976698300017737