The University of Southampton
University of Southampton Institutional Repository

The effect of a non-exhaustively defined set of classes on neural network classifications

The effect of a non-exhaustively defined set of classes on neural network classifications
The effect of a non-exhaustively defined set of classes on neural network classifications
Freedom from assumptions about the data set used is one attraction of neural network classifiers. However, neural network classification is not assumption-free. It is typically assumed that the set of classes has been defined exhaustively. If this assumption is unsatisfied, cases of an untrained class will be present and commissioned into the set of trained classes to the detriment of classification accuracy, for both hard and soft classifications. This is illustrated with MLP and RBF neural networks together with suggestions of how to reduce the problem for both hard and soft image classifications
geophysical signal processing, image classification, multilayer perceptrons, radial basis, function networks, remote sensing, mlp neural networks, rbf neural networks, classification accuracy, image classifications, neural network classifications, nonexhaustively defined classes, trained classes, untrained class
2731-2733
IEEE
Foody, G.M.
06e50027-603d-4a5b-88f5-af2bb6235a37
Foody, G.M.
06e50027-603d-4a5b-88f5-af2bb6235a37

Foody, G.M. (2001) The effect of a non-exhaustively defined set of classes on neural network classifications. In Geoscience and Remote Sensing Symposium, IGARSS '01. IEEE 2001 International, Sydney, Australia, 9-13 Jul 2001. IEEE. pp. 2731-2733 . (doi:10.1109/IGARSS.2001.978144).

Record type: Conference or Workshop Item (Paper)

Abstract

Freedom from assumptions about the data set used is one attraction of neural network classifiers. However, neural network classification is not assumption-free. It is typically assumed that the set of classes has been defined exhaustively. If this assumption is unsatisfied, cases of an untrained class will be present and commissioned into the set of trained classes to the detriment of classification accuracy, for both hard and soft classifications. This is illustrated with MLP and RBF neural networks together with suggestions of how to reduce the problem for both hard and soft image classifications

This record has no associated files available for download.

More information

Published date: 2001
Venue - Dates: conference; 2001-07-09; 2001-07-13, 2001-07-09 - 2001-07-13
Keywords: geophysical signal processing, image classification, multilayer perceptrons, radial basis, function networks, remote sensing, mlp neural networks, rbf neural networks, classification accuracy, image classifications, neural network classifications, nonexhaustively defined classes, trained classes, untrained class

Identifiers

Local EPrints ID: 15216
URI: http://eprints.soton.ac.uk/id/eprint/15216
PURE UUID: c6f5feac-5cf7-4102-8c87-c712226219aa

Catalogue record

Date deposited: 12 Apr 2005
Last modified: 15 Mar 2024 05:36

Export record

Altmetrics

Contributors

Author: G.M. Foody

Download statistics

Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.

View more statistics

Atom RSS 1.0 RSS 2.0

Contact ePrints Soton: eprints@soton.ac.uk

ePrints Soton supports OAI 2.0 with a base URL of http://eprints.soton.ac.uk/cgi/oai2

This repository has been built using EPrints software, developed at the University of Southampton, but available to everyone to use.

We use cookies to ensure that we give you the best experience on our website. If you continue without changing your settings, we will assume that you are happy to receive cookies on the University of Southampton website.

×