Share Email Print

Optical Engineering

Coding design for error correcting output codes based on perceptron
Author(s): Jin-Deng Zhou; Xiao-Dan Wang; Hong-Jian Zhou; Yong-Hua Cui; Sun Jing
Format Member Price Non-Member Price
PDF $20.00 $25.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

It is known that error-correcting output codes (ECOC) is a common way to model multiclass classification problems, in which the research of encoding based on data is attracting more and more attention. We propose a method for learning ECOC with the help of a single-layered perception neural network. To achieve this goal, the code elements of ECOC are mapped to the weights of network for the given decoding strategy, and an object function with the constrained weights is used as a cost function of network. After the training, we can obtain a coding matrix including lots of subgroups of class. Experimental results on artificial data and University of California Irvine with logistic linear classifier and support vector machine as the binary learner show that our scheme provides better performance of classification with shorter length of coding matrix than other state-of-the-art encoding strategies.

Paper Details

Date Published: 14 May 2012
PDF: 7 pages
Opt. Eng. 51(5) 057202 doi: 10.1117/1.OE.51.5.057202
Published in: Optical Engineering Volume 51, Issue 5
Show Author Affiliations
Jin-Deng Zhou, Air Force Engineering Univ. (China)
Xiao-Dan Wang, Air Force Engineering Univ. (China)
Hong-Jian Zhou, The Fourth Lab of Complex System (China)
Yong-Hua Cui, The Fourth Lab of Complex System (China)
Sun Jing, Dalian Airforce Communication NCO Academy (China)

© SPIE. Terms of Use
Back to Top