Bayesian methods for neural networks

Christopher M. Bishop

Bayesian methods for neural networks

Christopher M. Bishop

Aston University

Research output: Preprint or Working paper › Technical report

76 Downloads (Pure)

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
Place of Publication	Birmingham
Publisher	Aston University
Number of pages	18
Publication status	Published - 1995

Publication series

Name	NCRG
No.	95/009

Bibliographical note

Copyright © 1995, Christopher M. Bishop. This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License (https://creativecommons.org/licenses/by-nc-nd/4.0/).

Keywords

Bayesian
neural networks
learning
pattern recognition

Access to Document

NCRG_95_009.pdf
Copyright © 1995, Christopher M. Bishop. This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License (https://creativecommons.org/licenses/by-nc-nd/4.0/).
Licence: CC BY-NC-ND 4.0

1 Chapter

Bayesian methods for neural networks
Bishop, C. M., 1995, Oxford Lectures on Neural Networks. Tarassenko, L., Rolls, E. & Sherrington, D. (eds.). Oxford: Oxford University Press
Research output: Chapter in Book/Published conference output › Chapter

Cite this

@techreport{ee6e6f81138843169b994e72b61c5235,

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.}",

note = "Copyright {\textcopyright} 1995, Christopher M. Bishop. This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License (https://creativecommons.org/licenses/by-nc-nd/4.0/).",

year = "1995",

language = "English",

series = "NCRG",

publisher = "Aston University",

number = "95/009",

type = "WorkingPaper",

institution = "Aston University",

}

TY - UNPB

T1 - Bayesian methods for neural networks

AU - Bishop, Christopher M.

N1 - Copyright © 1995, Christopher M. Bishop. This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License (https://creativecommons.org/licenses/by-nc-nd/4.0/).

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 - Technical report

T3 - NCRG

BT - Bayesian methods for neural networks

PB - Aston University

CY - Birmingham

ER -

Bayesian methods for neural networks

Abstract

Publication series

Bibliographical note

Keywords

Access to Document

Fingerprint

Research output

Bayesian methods for neural networks

Cite this