Effect of Slow Switching of Ensemble Teachers in On-line Learning

  • Miyoshi Seiji
    Department of Electrical and Electronic Engineering, Faculty of Engineering Science, Kansai University
  • Okada Masato
    Division of Transdisciplinary Sciences, Graduate School of Frontier Sciences, The University of Tokyo RIKEN Brain Science Institute

Search this article

Abstract

We have analyzed the generalization performance of a student which slowly switches ensemble teachers. By calculating the generalization error analytically using statistical mechanics in the framework of on-line learning, we show that the dynamical behaviors of generalization error have a periodicity that is synchronized with the switching period and that the behaviors differ with the number of ensemble teachers. Furthermore, we show that the smaller the switching period is, the larger the difference in behavior is.

Journal

References(12)*help

See more

Related Projects

See more

Details 詳細情報について

Report a problem

Back to top