Title :
A linear transform that simplifies and improves neural-network classifiers
Author_Institution :
Army Res. Lab., Adelphi, MD, USA
Abstract :
This paper presents a linear transform that compresses data in a manner designed to improve the performance of a binary classifier. The transform, which is called the eigenspace separation transform, allows the reduction of the size of a neural network while enhancing its generalization accuracy as a binary classifier
Keywords :
pattern classification; binary classifier; data compression; eigenspace separation transform; linear transform; neural-network classifiers; Data compression; Karhunen-Loeve transforms; Laboratories; Mean square error methods; Milling machines; Neural networks; Powders; Principal component analysis; Telephony; Vectors;
Conference_Titel :
Neural Networks, 1996., IEEE International Conference on
Conference_Location :
Washington, DC
Print_ISBN :
0-7803-3210-5
DOI :
10.1109/ICNN.1996.549163
