相関情報抽出ネットと空間認識能力の教師なし学習

• 柴田 克成

  東京大学先端科学技術研究センター

• 岡部 洋一

  東京大学先端科学技術研究センター

書誌事項

タイトル別名

• Unsupervised Learning of the Spatial Recognition Ability Using the Correlated Information Extracting Neural Network

抄録

The Correlated Information Extracting Neural Network has been proposed to extract the common information among multiple kinds of inputs. Applying this neural network to a robot with a visual sensor, the distance to an object could be extracted as the correlated information between motional signals and visual signals after learning. In the case of stereo vision which uses two visual sensors, the output representing the distance, did not depend on the size of the object. When the signals of tactile sensor were added to the neural network, the robot could detect from the visual signals or from the motional signals if the robot touched the object.

収録刊行物

• 日本神経回路学会誌

  日本神経回路学会誌 3 (1), 11-16, 1996

  日本神経回路学会

詳細情報

• CRID: 1390001204467580800
• NII論文ID: 10008841111
• NII書誌ID: AA11658570
• DOI: 10.3902/jnns.3.11
• ISSN: 18830455
• ISSN: 1340766X
• 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