Login
Home > Research > EPrints

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

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. Piscataway, USA, Institute of Electrical and Electronics Engineers, 2731-2733. (doi: 10.1109/IGARSS.2001.978144)

Full text not available from this repository.

Official URL: http://dx.doi.org/10.1109/IGARSS.2001.978144

Description/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

Item Type:Book Section
Uncontrolled 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
Related URLs:http://dx.doi.org/10.1109/IGAR...001.978144
Subjects:G Geography. Anthropology. Recreation > GA Mathematical geography. Cartography
Divisions:University Structure - Pre August 2011 > School of Geography > Remote Sensing and Spatial Analysis
ePrint ID:15216
Deposited On:12 Apr 2005
Last Modified:02 Mar 2012 13:25

Associated Staff Only: edit my ePrint