Statistical Mechanical Analysis of Simultaneous Perturbation Learning

Seiji MIYOSHI; Hiroomi HIKAWA; Yutaka MAEDA

doi:10.1587/transfun.E92.A.1743

Regular Section

Statistical Mechanical Analysis of Simultaneous Perturbation Learning

Seiji MIYOSHI, Hiroomi HIKAWA, Yutaka MAEDA

Author information

Keywords: simultaneous perturbation, on-line learning, statistical mechanical method, generalization error

JOURNAL RESTRICTED ACCESS

2009 Volume E92.A Issue 7 Pages 1743-1746

DOI https://doi.org/10.1587/transfun.E92.A.1743

Details

Abstract

We show that simultaneous perturbation can be used as an algorithm for on-line learning, and we report our theoretical investigation on generalization performance obtained with a statistical mechanical method. Asymptotic behavior of generalization error using this algorithm is on the order of t to the minus one-third power, where t is the learning time or the number of learning examples. This order is the same as that using well-known perceptron learning.

Corresponding author

Register with J-STAGE for free!