A challenge towards how far the emergence of higher functions can be explained by reinforcement learning using a neural network
Project/Area Number |
19300070
|
Research Category |
Grant-in-Aid for Scientific Research (B)
|
Allocation Type | Single-year Grants |
Section | 一般 |
Research Field |
Perception information processing/Intelligent robotics
|
Research Institution | Oita University |
Principal Investigator |
SHIBATA Katsunari Oita University, 工学部, 准教授 (10260522)
|
Project Period (FY) |
2007 – 2010
|
Project Status |
Completed (Fiscal Year 2010)
|
Budget Amount *help |
¥7,800,000 (Direct Cost: ¥6,000,000、Indirect Cost: ¥1,800,000)
Fiscal Year 2010: ¥1,430,000 (Direct Cost: ¥1,100,000、Indirect Cost: ¥330,000)
Fiscal Year 2009: ¥1,560,000 (Direct Cost: ¥1,200,000、Indirect Cost: ¥360,000)
Fiscal Year 2008: ¥1,430,000 (Direct Cost: ¥1,100,000、Indirect Cost: ¥330,000)
Fiscal Year 2007: ¥3,380,000 (Direct Cost: ¥2,600,000、Indirect Cost: ¥780,000)
|
Keywords | 知能ロボット / 強化学習 / ニューラルネット / 高次機能 / リカレントニューラルネット / コミュニケーション学習 / エッジ画像 / 適正度の履歴 / 色の恒常性 / 知能創発 / 高次機能創発 / シンボル / 予測 / 探索 / 記憶 / 意味付け / 自律学習 / 合目的性 / 離散状態遷移 / 乗算ニューロン / 決定論的知的探索 / 空間的抽象化 / 時間的抽象化 |
Research Abstract |
Emergence of higher functions has been aimed based on autonomous learning by reinforcement learning using a neural network that connects from sensors to motors. Although no significant fruits could be shown as for the emergence of symbol processing, but the emergence of "abstraction", "memory", "prediction", or "exploration" through the learning from only rewards and punishments has been shown. For example, in the learning of a task using a movable camera in which the identification and memorization of arrow direction are necessary to get a reward, extraction of arrow direction from images and memorization of it were realized.
|
Report
(6 results)
Research Products
(40 results)