Analysis of On-Line Learning when a Moving Teacher Goes around a True Teacher

• Miyoshi Seiji

  Department of Electronic Engineering, Kobe City College of Technology

• Okada Masato

  Division of Transdisciplinary Sciences, Graduate School of Frontier Sciences, The University of Tokyo RIKEN Brain Science Institute JST PRESTO

抄録

In the framework of on-line learning, a learning machine might move around a teacher due to the differences in structures or output functions between the teacher and the learning machine or due to noises. The generalization performance of a new student supervised by a moving machine has been analyzed. A model composed of a fixed true teacher, a moving teacher and a student that are all linear perceptrons with noises has been treated analytically using statistical mechanics. It has been proven that the generalization errors of a student can be smaller than that of a moving teacher, even if the student only uses examples from the moving teacher.

収録刊行物

• Ｊｏｕｒｎａｌ　ｏｆ　ｔｈｅ　Ｐｈｙｓｉｃａｌ　Ｓｏｃｉｅｔｙ　ｏｆ　Ｊａｐａｎ

  Ｊｏｕｒｎａｌ　ｏｆ　ｔｈｅ　Ｐｈｙｓｉｃａｌ　Ｓｏｃｉｅｔｙ　ｏｆ　Ｊａｐａｎ 75 (2), 024003-, 2006

  一般社団法人 日本物理学会

キーワード

• on-line learning
• generalization error
• moving teacher
• true teacher
• unlearnable case

詳細情報

• CRID: 1390001204189882752
• NII論文ID: 210000105994
• NII論文ID: 110004086865
• NII書誌ID: AA00704814
• DOI: 10.1143/jpsj.75.024003
• BIBCODE: 2006JPSJ...75b4003M
• ISSN: 13474073
• ISSN: 00319015
• NDL書誌ID: 7813093
• Web Site: https://ndlsearch.ndl.go.jp/books/R000000004-I7813093
• Web Site: http://journals.jps.jp/doi/pdf/10.1143/JPSJ.75.024003
• 本文言語コード: en
• データソース種別:
  • JaLC
  • NDL
  • Crossref
  • CiNii Articles
  • KAKEN
• 抄録ライセンスフラグ: 使用不可