Rchr
J-GLOBAL ID：200901091278133498
Update date: Sep. 24, 2024
Shibata Katsunari
シバタ カツナリ | Shibata Katsunari
Affiliation and department：
Job title：
Professor
Homepage URL (2)：
http://shws.cc.oita-u.ac.jp/~shibata/home.html
,
http://shws.cc.oita-u.ac.jp/~shibata/home-j.html
Research field (3)：
Mechanics and mechatronics
, Robotics and intelligent systems
, Intelligent informatics
Research keywords (8)：
Emergence of Intelligence
, Higher Functions
, Function Emergence
, Chaotic Neural Network
, Recurrent Neural Network
, Deep Reinforcement Learning
, Reinforcement Learning
, neural network
Research theme for competitive and other funds (12)：
- 2020 - 2021 Establishment of Chaos-based Dynamic Reinforcement Learning as Taking an Essential Technology to Realize Emergence of Thinking in Advance
- 2015 - 2020 From "Exploration" To "Thinking" - Development of Chaos Dynamics through Reinforcement Learning
- 2011 - 2013 Exploration of a Breakthrough Technology for Emergence of Symbol Processing by Neuro-based Reinforcement Learning Considering Time Axis
- 2007 - 2010 A challenge towards how far the emergence of higher functions can be explained by reinforcement learning using a neural network
- 2003 - 2006 Autonomous, Harmonious and Purposive Acquisition of Various Functions of Robots by Reinforcement Learning and the Relation to the Intelligence Formation
- 2002 - 2005 Study on Body Dynamics Formation and Pattern Generation for Motor/Action Learning
- 2001 - 2002 Verification of Direct-Vision-Based Reinforcement Learning Using a Real Robot
- 1996 - 1996 A Basic Study on Learning Neural Network Models Considering Temporal Information
- 1996 - 1996 Research on the integration of sensor signal integration learning and reinforcement learning
- 1995 - 1995 Research on autonomous active learning machines that self-formulate obstacle avoidance through parallel learning of evaluation and action
- 1995 - 1995 Fundamental study on neural network models for pulsed neural devices
- 1994 - 1994 A neural network that acquires motion control by interacting with the environment
Show all
Papers (38)：
-
Katsunari Shibata, Takuya Ejima, Yuki Tokumaru, Toshitaka Matsuki. Sensitivity - Local index to control chaoticity or gradient globally -. Neural Networks. 2021. 143. 436-451
-
Toshitaka Matsuki, Katsunari Shibata. Learning Time Constant of Continuous-Time Neurons with Gradient Descent. Lecture Notes in Mechanical Engineering. 2020. 149-159
-
Toshitaka Matsuki, Souya Inoue, Katsunari Shibata. Q-learning with exploration driven by internal dynamics in chaotic neural network. 2020 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN). 2020
-
Katsunari Shibata, Takuya Ejima, Yuki Tokumaru, Toshitaka Matsuki. Sensitivity - Local Index to Control Chaoticity or Gradient Globally. CoRR. 2020. abs/2012.13134
-
Toshitaka Matsuki, Souya Inoue, Katsunari Shibata. Q-learning with exploration driven by internal dynamics in chaotic neural network. 2020 International Joint Conference on Neural Networks(IJCNN). 2020. 1-7
ｍore...
MISC (140)：
-
吉岡晴海, 松木俊貴, 柴田克成. Construction of Reservoir Network Using Sensitivity Adjustment Learning. 計測自動制御学会九州支部学術講演会予稿集(CD-ROM). 2020. 39th
-
大石将人, 松木俊貴, 柴田克成. Effect of Chaos on Supervised Learning of State Transition Tasks Using Recurrent Neural Networks. 計測自動制御学会九州支部学術講演会予稿集(CD-ROM). 2020. 39th
-
SHIBATA Katsunari. Causality Trace : Effective Retrospective Learning by Introducing Parallel and Subjective Time Scales. IEICE technical report. Neurocomputing. 2014. 113. 500. 157-162
-
Acquisition of Prediction-based Flexible Actions with Continuous Motions by Actor-Q-Learning. 2013. 2013. 29. 91-96
-
SHIBATA Katsunari, KURIZAKI Shunsuke. Emergence of "Color Constancy" through Learning of Behaviors by Reinforcement Learning with a Neural Network. IEICE technical report. Neurocomputing. 2013. 112. 480. 215-220
ｍore...
Patents (2)：
Books (2)：
-
ロボット情報学ハンドブック
ナノオプトニクス・エナジー,近代科学社 (発売) 2010 ISBN:9784764955073
-
脳科学大事典
朝倉書店 2000 ISBN:4254101562
Works (2)：
-
実ロボットによるニューロベース強化学習の自律学習機能の検証
2001 -
-
Autonomous Learning Ability of Neuro-based Reinforcement Learning in real robots
2001 -
Education (3)：
- 1992 - 1993 The University of Tokyo The Graduate School of Engineering
- 1987 - 1989 The University of Tokyo The Graduate School of Engineering (Master Course) Department of Mechanical Engineering
- 1983 - 1987 The University of Tokyo The Faculty of Engineering Department of Mechanical Engineering
Professional career (1)：
- Dr. Engineering (The University of Tokyo)
Work history (8)：
- 2019/10 - 2021/03 Oita University Faculty of Science and Technology Department of Innovative Engineering Professor
- 2007/04 - 2019/09 Oita University. Faculty of Engineering Associate Professor
- 2001/04 - 2007/03 Oita University
- 2005/02 - 2005/09 University of Aberta Dept. of Computing Science Visiting Professor
- 2000 - 2001 Oita University Faculty of Engineering Lecturer
- 1997/04 - 2000/03 Tokyo Institute of Technology Interdisciplinary Science and Engineering Research Associate
- 1993/10 - 1997/03 The University of Tokyo Research Center for Advanced Science and Technology Research Associate
- 1989 - 1992 Hitachi, Ltd., Central Research Laboratory Researcher
Show all
Committee career (2)：
- 2012 - 2016 日本神経回路学会 理事
- 計測自動制御学会 ニューラルネットワーク部会運営委員、 自律分散システム部会運営委員、 九州支部事業委員
Awards (1)：
- 2021/09 - Japanese Neural Network Society. Best Paper Award Adaptive balancing of exploration and exploitation around the edge of chaos in internal-chaos-based learning
Association Membership(s) (8)：
計測自動制御学会
, 日本神経回路学会
, 電子情報通信学会
, IEEE
, JNNS
, SICE
, IEICE
, IEEE
