強化学習による能動認識能力の学習  [in Japanese] Learning of Active Perception Based on Reinforcement Learning  [in Japanese]

Access this Article

Search this Article

Author(s)

    • 西野 哲生 NISHINO Tetsuo
    • 東京大学先端科学技術研究センター Research Center for Advanced Science and Technology (RCAST), University of Tokyo
    • 岡部 洋一 OKABE Yoichi
    • 東京大学先端科学技術研究センター Research Center for Advanced Science and Technology (RCAST), University of Tokyo

Abstract

The aim is to perform to realize a learning system for active perception using a neural network. It obtains inputs only from a movable visual sensor and learns both appropriate recognition and sensor motions for effective perception. The proposed learning method is based on reinforcement learning using reinforcement signals calculated from the recognition results. We conclude from simulations that it enables the system to move a visual sensor to the appropriate location and finally classify presented patterns correctly. The recognition rate was better than that in a simulation for comparison where the sensor was fixed at the initial location.

Journal

  • The Brain & Neural Networks

    The Brain & Neural Networks 3(4), 126-134, 1996-12-05

    Japanese Neural Network Society

References:  13

Cited by:  2

Codes

  • NII Article ID (NAID)
    10008841198
  • NII NACSIS-CAT ID (NCID)
    AA11658570
  • Text Lang
    JPN
  • Article Type
    Journal Article
  • ISSN
    1340766X
  • Data Source
    CJP  CJPref  J-STAGE 
Page Top