3P2-P06 A Computational Model of Early Development of Predictive Eye Movement(Neurorobotics & Cognitive Robotics)

• Copete Jorge Luis

  Department of Adaptive Machine Systems Graduate School of Engineering, Osaka University

• Nagai Yukie

  Department of Adaptive Machine Systems Graduate School of Engineering, Osaka University

• Asada Minoru

  Department of Adaptive Machine Systems Graduate School of Engineering, Osaka University

抄録

In this work, we propose a computational model employing a recurrent neural network for modeling the developmental process of action prediction ability. Our hypothesis is that temporal memory is a driving force mechanism for the development of this ability. While keeping consistency with the psychological findings, our experimental results confirmed the hypothesis, showing that memory capacity has a strong influence on the development of prediction abilities.

収録刊行物

• ロボティクス・メカトロニクス講演会講演概要集

  ロボティクス・メカトロニクス講演会講演概要集 2014 (0), _3P2-P06_1-_3P2-P06_4, 2014

  一般社団法人 日本機械学会

キーワード

• Cognitive developmental Robotics
• Recurrent Neural Network
• Visual Attention

詳細情報

• CRID: 1390001205939622784
• NII論文ID: 110009967418
• DOI: 10.1299/jsmermd.2014._3p2-p06_1
• ISSN: 24243124
• Web Site: https://www.jstage.jst.go.jp/article/jsmermd/2014/0/2014__3P2-P06_1/_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