HOME HELP FEEDBACK SUBSCRIPTIONS ARCHIVE SEARCH TABLE OF CONTENTS		QUICK SEARCH:   [advanced] Author: Keyword(s): Year:  Vol:  Page:

This Article Full Text Full Text (PDF) Alert me when this article is cited Alert me if a correction is posted Services Similar articles in this journal Similar articles in PubMed Alert me to new issues of the journal Download to citation manager Citing Articles Citing Articles via Google Scholar Google Scholar Articles by Duckro, D. E. Articles by Gardner, S. J. Search for Related Content PubMed PubMed Citation Articles by Duckro, D. E. Articles by Gardner, S. J., III

Neural Network Pruning with Tukey-Kramer Multiple Comparison Procedure

duckro{at}yahoo.com, Air Force Institute of Technology, Department of Mathematics and Statistics, Wright-Patterson Air Force Base, Ohio 45433, U.S.A.

Dennis W. Quinn

dennis.quinn{at}afit.edu, Air Force Institute of Technology, Department of Mathematics and Statistics, Wright-Patterson Air Force Base, Ohio 45433, U.S.A.

Samuel J. Gardner, III

Air Force Institute of Technology, Department of Mathematics and Statistics, Wright-Patterson Air Force Base, Ohio 45433, U.S.A.

Reducing a neural network's complexity improves the ability of the network to generalize future examples. Like an overfitted regression function, neural networks may miss their target because of the excessive degrees of freedom stored up in unnecessary parameters. Over the past decade, the subject of pruning networks produced nonstatistical algorithms like Skeletonization, Optimal Brain Damage, and Optimal Brain Surgeon as methods to remove connections with the least salience. The method proposed here uses the bootstrap algorithm to estimate the distribution of the model parameter saliences. Statistical multiple comparison procedures are then used to make pruning decisions. We show this method compares well with Optimal Brain Surgeon in terms of ability to prune and the resulting network performance.