Bayesian Learning For Neural Networks

Paperback

byRadford M. Neal

not yet rated|write a review
Artificial "neural networks" are widely used as flexible models for classification and regression applications, but questions remain about how the power of these models can be safely exploited when training data is limited. This book demonstrates how Bayesian methods allow complex neural network models to be used without fear of the "overfitting" that can occur with traditional training methods. Insight into the nature of these complex Bayesian models is provided by a theoretical investigation of the priors over functions that underlie them. A practical implementation of Bayesian neural network learning using Markov chain Monte Carlo methods is also described, and software for it is freely available over the Internet. Presupposing only basic knowledge of probability and statistics, this book should be of interest to researchers in statistics, engineering, and artificial intelligence.

Pricing and Purchase Info

$212.17 online
$219.95 list price
In stock online
Ships free on orders over $25

From the Publisher

Artificial "neural networks" are widely used as flexible models for classification and regression applications, but questions remain about how the power of these models can be safely exploited when training data is limited. This book demonstrates how Bayesian methods allow complex neural network models to be used without fear of the "o...

Format:PaperbackDimensions:204 pages, 9.25 × 6.1 × 0 inPublisher:Springer New York

The following ISBNs are associated with this title:

ISBN - 10:0387947248

ISBN - 13:9780387947242

Look for similar items by category:

Customer Reviews of Bayesian Learning For Neural Networks

Reviews

Extra Content

Table of Contents

Preface; 1: Introduction; 2: Priors for Infinite Networks; 3: Monte Carlo Implementation; 4: Evaluation of Neural Network Models; 5: Conclusions and Further Work; A: Details of the Implementation; B: Obtaining the Software; Bibliography; Index