본문 바로가기
  • Home

A Layer-by-Layer Learning Algorithm using Correlation Coefficient for Multilayer Perceptrons

  • Journal of The Korea Society of Computer and Information
  • Abbr : JKSCI
  • 2011, 16(8), pp.39-48
  • Publisher : The Korean Society Of Computer And Information
  • Research Area : Engineering > Computer Science

곽영태 1

1전북대학교

Accredited

ABSTRACT

Ergezinger's method, one of the layer-by-layer algorithms used for multilyer perceptrons, consists of an output node and can make premature saturations in the output's weight because of using linear least squared method in the output layer. These saturations are obstacles to learning time and covergence. Therefore, this paper expands Ergezinger's method to be able to use an output vector instead of an output node and introduces a learning rate to improve learning time and convergence. The learning rate is a variable rate that reflects the correlation coefficient between new weight and previous weight while updating hidden's weight. To compare the proposed method with Ergezinger's method, we tested iris recognition and nonlinear approximation. It was found that the proposed method showed better results than Ergezinger's method in learning convergence. In the CPU time considering correlation coefficient computation, the proposed method saved about 35% time than the previous method.

Citation status

* References for papers published after 2022 are currently being built.