Forced formation of a geometrical feature space by a neural network model with supervised learning

• TAKEDA T.

  the Laboratory of Physiological Sciences, School of Nursing, Jichi Medical School

• Mizoe Hiroki

  the Faculty of Engineering, Utsunomiya University

• Kishi Koichiro

  the Department of Pharmacology, Jichi Medical School

• Matsuoka Takahide

  the Faculty of Engineering, Utsunomiya University

抄録

To investigate necessary conditions for the object recognition by simulations using neural network model is one of ways to acquire suggestions for understanding the neuronal representation of objects in the brain. In the present study, we trained a three layered neural network to form a geometrical feature representation in its output layer using back-propagation algorithm. After training using 73 learning examples, 65 testing patterns made by various combinations of above features could be recognized with the network at a rate of 95.3 appropriate response. We could classify four types of hidden layer units on the basis of effects on the output layer.

収録刊行物

• IEICE Trans. Fundamentals, A

  IEICE Trans. Fundamentals, A 76 (7), 1129-1132, 1993

  一般社団法人電子情報通信学会

キーワード

• feature space
• geometrical pattern
• neural network
• supervised learning
• rotation invariant recognition

詳細情報

• CRID: 1572824502325701632
• NII論文ID: 110003215571
• 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