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 Alert me to new issues of the journal Download to citation manager Google Scholar Articles by Toh, K.-A. PubMed Articles by Toh, K.-A.

Deterministic Neural Classification

katoh{at}yonsei.ac.kr Biometrics Engineering Research Center, School of Electrical and Electronic Engineering, Yonsei University, Seoul 120-749, Korea

This letter presents a minimum classification error learning formulation for asingle-layer feedforward network (SLFN). By approximating the nonlinear counting stepfunction using a quadratic function, the classification error rate is shown to bedeterministically solvable. Essentially the derived solution is related to an existingweighted least-squares method with class-specific weights set according to thesize of data set. By considering the class-specific weights as adjustable parameters, thelearning formulation extends the classification robustness of the SLFN withoutsacrificing its intrinsic advantage of being a closed-form algorithm. While the method isapplicable to other linear formulations, our empirical results indicate SLFN's effectiveness on classification generalization.