| Project/Area Number |
13450176
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (B)
|
| Allocation Type | Single-year Grants |
|---|
| Section | 一般 |
|---|
| Research Field |
Control engineering
|
|---|
| Research Institution | Yamaguchi University |
|---|
Principal Investigator |
OBAYASHI Masanao Yamaguchi University, Faculty of Engineering, Professor, 工学部, 教授 (60213849)
|
|---|
| Co-Investigator(Kenkyū-buntansha) |
KUREMOTO Takashi Yamaguchi University, Faculty of Engineering, Research Assistant, 工学部, 教務員 (40294657)
KOBAYASHI Kunikazu Yamaguchi University, Faculty of Engineering, Research Associate, 工学部, 助手 (40263793)
|
|---|
| Project Period (FY) |
2001 – 2003
|
| Project Status |
Completed (Fiscal Year 2003)
|
| Budget Amount *help |
¥6,500,000 (Direct Cost: ¥6,500,000)
Fiscal Year 2003: ¥1,100,000 (Direct Cost: ¥1,100,000)
Fiscal Year 2002: ¥2,400,000 (Direct Cost: ¥2,400,000)
Fiscal Year 2001: ¥3,000,000 (Direct Cost: ¥3,000,000)
|
|---|
| Keywords | Learning / Chaotic Neural network / Reinforcement Learning / Nonlinear system control / Chaos / Edge of chaos / Associative memory / Robot / 階層型連想記憶 / 非線形制御 / 免疫システム / ニューラルネットワーク / 海馬連合野モデル / 時系列データ / 1対多 / ロボット制御 / カオスの辺縁 / 関数型記憶行列 / 情報生成 / 自己組織化 |
|---|
| Research Abstract |
To realize the autonomous system with inner modeled associative memory, it is very useful to research the function of the human brain and learning method of the living things. Under these considerations, we mainly developed
i) for reinforcement learning, a faster learning method with asymmetric probability density function to realize trial and error effectively
ii) for reinforcement learning, a learning method introducing the idea of time-varying parameters in order to adapt to dynamical environments which change rapidly
iii) chaotic neural networks with function typed synaptic weights which enable easier retrieval of stored patterns than conventional in the case that each stored patterns have strong correlation each other
iv) a retrieval method for time-series data, particularly for plural time-series data which have same first data but different after that
v) robust chaotic control method introducing the idea of edge of chaos that the system is in the state between chaotic state and non-chaotic state
vi) high precision of chaotic time series prediction by introducing the stochastic ascent gradient reinforcement learning method as prediction method
These validity has been clarified by simulation studies
|
