Statistical Mechanical Analysis of Simultaneous Perturbation Learning

• MIYOSHI Seiji

  Department of Electrical and Electronic Engineering, Faculty of Engineering Science, Kansai University

• HIKAWA Hiroomi

  Department of Electrical and Electronic Engineering, Faculty of Engineering Science, Kansai University

• MAEDA Yutaka

  Department of Electrical and Electronic Engineering, Faculty of Engineering Science, Kansai University

抄録

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.

収録刊行物

• IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences

  IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences E92-A (7), 1743-1746, 2009

  一般社団法人 電子情報通信学会

キーワード

• simultaneous perturbation
• on-line learning
• statistical mechanical method
• generalization error

詳細情報

• CRID: 1390001206310179200
• NII論文ID: 10026858562
• NII書誌ID: AA10826239
• DOI: 10.1587/transfun.e92.a.1743
• ISSN: 17451337
• ISSN: 09168508
• Web Site: http://www.jstage.jst.go.jp/article/transfun/E92.A/7/E92.A_7_1743/_pdf
• 本文言語コード: en
• データソース種別:
  • JaLC
  • Crossref
  • CiNii Articles
• 抄録ライセンスフラグ: 使用不可