Lecture Notes in Statistics

Bayesian Learning for Neural Networks

Authors: Neal, Radford M.

Free Preview

Buy this book

eBook 106,99 €
price for Spain (gross)
  • ISBN 978-1-4612-0745-0
  • Digitally watermarked, DRM-free
  • Included format: PDF
  • Immediate eBook download after purchase and usable on all devices
  • Bulk discounts available
Softcover 135,19 €
price for Spain (gross)
About this book

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.

Table of contents (5 chapters)

Table of contents (5 chapters)

Buy this book

eBook 106,99 €
price for Spain (gross)
  • ISBN 978-1-4612-0745-0
  • Digitally watermarked, DRM-free
  • Included format: PDF
  • Immediate eBook download after purchase and usable on all devices
  • Bulk discounts available
Softcover 135,19 €
price for Spain (gross)
Loading...

Recommended for you

Loading...

Bibliographic Information

Bibliographic Information
Book Title
Bayesian Learning for Neural Networks
Authors
Series Title
Lecture Notes in Statistics
Series Volume
118
Copyright
1996
Publisher
Springer-Verlag New York
Copyright Holder
Springer Science+Business Media New York
eBook ISBN
978-1-4612-0745-0
DOI
10.1007/978-1-4612-0745-0
Softcover ISBN
978-0-387-94724-2
Series ISSN
0930-0325
Edition Number
1
Number of Pages
204
Topics