By Topic

Method for calculating first-order derivative based feature saliency information in a trained neural network and its application to handwritten digit recognition

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

Formats Non-Member Member
$33 $33
Learn how you can qualify for the best price for this item!
Become an IEEE Member or Subscribe to
IEEE Xplore for exclusive pricing!
close button

puzzle piece

IEEE membership options for an individual and IEEE Xplore subscriptions for an organization offer the most affordable access to essential journal articles, conference papers, standards, eBooks, and eLearning courses.

Learn more about:

IEEE membership

IEEE Xplore subscriptions

2 Author(s)
A. D. Parkins ; Signal Process. & Commun. Group, Univ. of Liverpool, UK ; A. K. Nandi

A generalised method is presented for calculating the first-order derivative relationship between inputs and outputs in a trained neural network and the use of these derivatives to perform feature selection. We use a handwritten digit data set as a source for comparing this feature selection method with a standard genetic algorithm feature selection method.

Published in:

IEE Proceedings - Vision, Image and Signal Processing  (Volume:152 ,  Issue: 2 )