Using Bayesian neural networks to classify segmented images

Francesco Vivarelli; Christopher K. I. Williams

doi:10.1049/cp:19970738

Using Bayesian neural networks to classify segmented images

Francesco Vivarelli, Christopher K. I. Williams

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

Abstract

We present results that compare the performance of neural networks trained with two Bayesian methods, (i) the Evidence Framework of MacKay (1992) and (ii) a Markov Chain Monte Carlo method due to Neal (1996) on a task of classifying segmented outdoor images. We also investigate the use of the Automatic Relevance Determination method for input feature selection.

Original language	English
Title of host publication	Fifth International Conference on Artificial Neural Networks
Place of Publication	Cambridge, UK
Publisher	Aston University
Pages	268-273
Number of pages	6
Volume	1997
ISBN (Print)	0852966903
DOIs	https://doi.org/10.1049/cp:19970738
Publication status	Published - 9 Jul 1997

Keywords

neural networks
Automatic Relevance Determination
feature selection

Access to Document

10.1049/cp:19970738

Using Bayesian neural networks to classify segmented imagesFinal published version, 594 KB

Cite this

@inbook{bfa0ca49737a47598de791e7e240be86,

title = "Using Bayesian neural networks to classify segmented images",

abstract = "We present results that compare the performance of neural networks trained with two Bayesian methods, (i) the Evidence Framework of MacKay (1992) and (ii) a Markov Chain Monte Carlo method due to Neal (1996) on a task of classifying segmented outdoor images. We also investigate the use of the Automatic Relevance Determination method for input feature selection.",

keywords = "neural networks, Automatic Relevance Determination, feature selection",

author = "Francesco Vivarelli and Williams, {Christopher K. I.}",

year = "1997",

month = jul,

day = "9",

doi = "10.1049/cp:19970738",

language = "English",

isbn = "0852966903",

volume = "1997",

pages = "268--273",

booktitle = "Fifth International Conference on Artificial Neural Networks",

publisher = "Aston University",

}

TY - CHAP

T1 - Using Bayesian neural networks to classify segmented images

AU - Vivarelli, Francesco

AU - Williams, Christopher K. I.

PY - 1997/7/9

Y1 - 1997/7/9

N2 - We present results that compare the performance of neural networks trained with two Bayesian methods, (i) the Evidence Framework of MacKay (1992) and (ii) a Markov Chain Monte Carlo method due to Neal (1996) on a task of classifying segmented outdoor images. We also investigate the use of the Automatic Relevance Determination method for input feature selection.

AB - We present results that compare the performance of neural networks trained with two Bayesian methods, (i) the Evidence Framework of MacKay (1992) and (ii) a Markov Chain Monte Carlo method due to Neal (1996) on a task of classifying segmented outdoor images. We also investigate the use of the Automatic Relevance Determination method for input feature selection.

KW - neural networks

KW - Automatic Relevance Determination

KW - feature selection

UR - http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=607529&isnumber=13303

UR - http://www.scopus.com/inward/record.url?scp=0030649836&partnerID=8YFLogxK

U2 - 10.1049/cp:19970738

DO - 10.1049/cp:19970738

M3 - Chapter

SN - 0852966903

VL - 1997

SP - 268

EP - 273

BT - Fifth International Conference on Artificial Neural Networks

PB - Aston University

CY - Cambridge, UK

ER -

Using Bayesian neural networks to classify segmented images

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this