Using Bayesian neural networks to classify segmented images

F. Vivarelli; C.K.I. Williams

doi:10.1049/cp:19970738

Using Bayesian neural networks to classify segmented images

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract / Description of output

We present results that compare the performance of neural networks trained with two Bayesian methods, (i) the evidence framework of D.J.C. MacKay (1992) and (ii) a Markov chain Monte Carlo method due to R.M. 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	Artificial Neural Networks, Fifth International Conference on (Conf. Publ. No. 440)
Publisher	IET
Pages	268-273
Number of pages	6
ISBN (Print)	0-85296-690-3
DOIs	https://doi.org/10.1049/cp:19970738
Publication status	Published - 1 Jul 1997

Keywords / Materials (for Non-textual outputs)

neural nets
Bayesian neural networks
Markov chain Monte Carlo method
automatic relevance determination method
evidence framework
input feature selection
performance
segmented images classification

Access to Document

10.1049/cp:19970738

http://ieeexplore.ieee.org/xpl/articleDetails.jsp?arnumber=607529

Cite this

@inproceedings{f126cc7c4992469f9bd72cc0b572e71e,

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 D.J.C. MacKay (1992) and (ii) a Markov chain Monte Carlo method due to R.M. 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 nets, Bayesian neural networks, Markov chain Monte Carlo method, automatic relevance determination method, evidence framework, input feature selection, performance, segmented images classification",

author = "F. Vivarelli and C.K.I. Williams",

year = "1997",

month = jul,

day = "1",

doi = "10.1049/cp:19970738",

language = "English",

isbn = "0-85296-690-3",

pages = "268--273",

booktitle = "Artificial Neural Networks, Fifth International Conference on (Conf. Publ. No. 440)",

publisher = "IET",

}

TY - GEN

T1 - Using Bayesian neural networks to classify segmented images

AU - Vivarelli, F.

AU - Williams, C.K.I.

PY - 1997/7/1

Y1 - 1997/7/1

N2 - We present results that compare the performance of neural networks trained with two Bayesian methods, (i) the evidence framework of D.J.C. MacKay (1992) and (ii) a Markov chain Monte Carlo method due to R.M. 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 D.J.C. MacKay (1992) and (ii) a Markov chain Monte Carlo method due to R.M. 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 nets

KW - Bayesian neural networks

KW - Markov chain Monte Carlo method

KW - automatic relevance determination method

KW - evidence framework

KW - input feature selection

KW - performance

KW - segmented images classification

U2 - 10.1049/cp:19970738

DO - 10.1049/cp:19970738

M3 - Conference contribution

SN - 0-85296-690-3

SP - 268

EP - 273

BT - Artificial Neural Networks, Fifth International Conference on (Conf. Publ. No. 440)

PB - IET

ER -

Using Bayesian neural networks to classify segmented images

Abstract / Description of output

Keywords / Materials (for Non-textual outputs)

Access to Document

Fingerprint

Cite this