Please use this identifier to cite or link to this item: http://hdl.handle.net/10397/11938
Title: Determining the relevance of input features for multilayer perceptrons
Authors: Zeng, X
Huang, Y
Yeung, DS
Keywords: Function approximation
Multilayer perceptrons
Redundancy
Issue Date: 2003
Publisher: IEEE
Source: IEEE International Conference on Systems, Man and Cybernetics, 2003, 5-8 October 2003, v. 1, p. 874-879 How to cite?
Abstract: This paper presents an approach to determine the relevance of individual input attributes for trained Multilayer Perceptrons (MLPs). To reflect the impact of an input attribute on the output of an MLP, the relevance is aimed at representing the output sensitivity of the MLP to the attribute variation. The sensitivity is defined as the mathematical expectation of output deviations of an MLP due to its input deviation with respect to overall input patterns. The basic idea for the introduction of such a relevance measure is that a well-trained MLP can capture salient features of the problem it deals with and thus become more sensitive to those input attributes that make more contributions to the MLP's behavior. The relevance can be employed as a relative criterion for assessing individual input attributes. The results from the experiments on two typical problems demonstrate the effectiveness of the relevance in identifying irrelevant input attribute.
URI: http://hdl.handle.net/10397/11938
ISBN: 0-7803-7952-7
ISSN: 1062-922X
DOI: 10.1109/ICSMC.2003.1243925
Appears in Collections:Conference Paper

Access
View full-text via PolyU eLinks SFX Query
Show full item record

Page view(s)

31
Last Week
1
Last month
Checked on Aug 13, 2017

Google ScholarTM

Check

Altmetric



Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.