Bayesian methods for neural networks

Christopher M. Bishop

Bayesian methods for neural networks

Christopher M. Bishop

Research output: Chapter in Book/Published conference output › Chapter

Abstract

Bayesian techniques have been developed over many years in a range of different fields, but have only recently been applied to the problem of learning in neural networks. As well as providing a consistent framework for statistical pattern recognition, the Bayesian approach offers a number of practical advantages including a potential solution to the problem of over-fitting. This chapter aims to provide an introductory overview of the application of Bayesian methods to neural networks. It assumes the reader is familiar with standard feed-forward network models and how to train them using conventional techniques.

Original language	English
Title of host publication	Oxford Lectures on Neural Networks
Editors	L. Tarassenko, E. Rolls, D. Sherrington
Place of Publication	Oxford
Publisher	Oxford University Press
Publication status	Published - 1995

Keywords

bayesian
neural networks
learning
pattern recognition

1 Technical report

Bayesian methods for neural networks
Bishop, C. M., 1995, Birmingham: Aston University, 18 p.
Research output: Preprint or Working paper › Technical report

File

Cite this

@inbook{f9e1e8259d4d4d5dae6904b0e1b0e262,

title = "Bayesian methods for neural networks",

abstract = "Bayesian techniques have been developed over many years in a range of different fields, but have only recently been applied to the problem of learning in neural networks. As well as providing a consistent framework for statistical pattern recognition, the Bayesian approach offers a number of practical advantages including a potential solution to the problem of over-fitting. This chapter aims to provide an introductory overview of the application of Bayesian methods to neural networks. It assumes the reader is familiar with standard feed-forward network models and how to train them using conventional techniques.",

keywords = "bayesian, neural networks, learning, pattern recognition",

author = "Bishop, {Christopher M.}",

year = "1995",

language = "English",

editor = "L. Tarassenko and E. Rolls and D. Sherrington",

booktitle = "Oxford Lectures on Neural Networks",

publisher = "Oxford University Press",

address = "United Kingdom",

}

TY - CHAP

T1 - Bayesian methods for neural networks

AU - Bishop, Christopher M.

PY - 1995

Y1 - 1995

N2 - Bayesian techniques have been developed over many years in a range of different fields, but have only recently been applied to the problem of learning in neural networks. As well as providing a consistent framework for statistical pattern recognition, the Bayesian approach offers a number of practical advantages including a potential solution to the problem of over-fitting. This chapter aims to provide an introductory overview of the application of Bayesian methods to neural networks. It assumes the reader is familiar with standard feed-forward network models and how to train them using conventional techniques.

AB - Bayesian techniques have been developed over many years in a range of different fields, but have only recently been applied to the problem of learning in neural networks. As well as providing a consistent framework for statistical pattern recognition, the Bayesian approach offers a number of practical advantages including a potential solution to the problem of over-fitting. This chapter aims to provide an introductory overview of the application of Bayesian methods to neural networks. It assumes the reader is familiar with standard feed-forward network models and how to train them using conventional techniques.

KW - bayesian

KW - neural networks

KW - learning

KW - pattern recognition

M3 - Chapter

BT - Oxford Lectures on Neural Networks

A2 - Tarassenko, L.

A2 - Rolls, E.

A2 - Sherrington, D.

PB - Oxford University Press

CY - Oxford

ER -

Bayesian methods for neural networks

Abstract

Keywords

Fingerprint

Research output

Bayesian methods for neural networks

Cite this