Embedded feature ranking for ensemble MLP classifiers

Windeatt, T, Duangsoithong, R and Smith, R (2011) Embedded feature ranking for ensemble MLP classifiers IEEE Transactions on Neural Networks, 22 (6). pp. 988-994.

Preview	Text windeatt_transnnsh3.pdf - Accepted version Manuscript Available under License : See the attached licence file. Download (504kB)
	Text (licence) licence.txt Download (1kB)

Abstract

A feature ranking scheme for multilayer perceptron (MLP) ensembles is proposed, along with a stopping criterion based upon the out-of-bootstrap estimate. To solve multi-class problems feature ranking is combined with modified error-correcting output coding. Experimental results on benchmark data demonstrate the versatility of the MLP base classifier in removing irrelevant features.

Item Type:	Article
Divisions :	Faculty of Engineering and Physical Sciences > Electronic Engineering > Centre for Vision Speech and Signal Processing
Authors :	Name Email ORCID Windeatt, T Duangsoithong, R Smith, R
Date :	2011
DOI :	10.1109/TNN.2011.2138158
Depositing User :	Symplectic Elements
Date Deposited :	22 Jul 2011 11:02
Last Modified :	31 Oct 2017 14:08
URI:	http://epubs.surrey.ac.uk/id/eprint/6484

Actions (login required)

View Item

Downloads