Geometric Properties of Quasi-Additive Learning Algorithms

• IKEDA Kazushi

  Kyoto University

抄録

The family of Quasi-Additive (QA) algorithms is a natural generalization of the perceptron learning, which is a kind of on-line learning having two parameter vectors: One is an accumulation of input vectors and the other is a weight vector for prediction associated with the former by a nonlinear function. We show that the vectors have a dually-flat structure from the information-geometric point of view, and this representation makes it easier to discuss the convergence properties.

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 89 (10), 2812-2817, 2006-10-01

  一般社団法人電子情報通信学会

キーワード

• quasi-additive algorithms
• perceptron
• information geometry

詳細情報

• CRID: 1572543027451325440
• NII論文ID: 110007537759
• NII書誌ID: AA10826239
• ISSN: 09168508
• 本文言語コード: en
• データソース種別:
  • CiNii Articles