| Project/Area Number |
10650433
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (C)
|
| 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, Accociate Professor, 工学部, 助教授 (60213849)
|
|---|
| Co-Investigator(Kenkyū-buntansha) |
MURATA Junichi Kyushu University, Graduate School of Information Science and Electrical Engineering, Associate Professor, 大学院・システム情報科学研究院, 助教授 (60190914)
HIRASAWA Kotaro Kyushu University, Graduate School of Information Science and Electrical Engineering, Professor, 大学院・システム情報科学研究院, 教授 (70253474)
KOBAYASHI Kunikazu Yamaguchi University, Faculty of Engineering, Research Associate, 工学部, 助手 (40263793)
|
|---|
| Project Period (FY) |
1998 – 2000
|
| Project Status |
Completed (Fiscal Year 2000)
|
| Budget Amount *help |
¥2,700,000 (Direct Cost: ¥2,700,000)
Fiscal Year 2000: ¥500,000 (Direct Cost: ¥500,000)
Fiscal Year 1999: ¥600,000 (Direct Cost: ¥600,000)
Fiscal Year 1998: ¥1,600,000 (Direct Cost: ¥1,600,000)
|
|---|
| Keywords | Learning / Neural network / Reinforcement Learning / Nonlinear system control / Chaos / Genetic algorithm / Associative memory / fuzzy / モデル化 / 制御 / 不完全観測 / オブザーバ / 高速化 / ロバスト性 |
|---|
| Research Abstract |
To model and control the nonlinear complex system, 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) an indirect encoding method with genetic algorithm to decide an optimal neural network structure,
ii) a method for faster neural networks learning to make a neural network control system,
iii) a control system structure to makes the system robust by using the second order derivatives of universal learning network,
iv) an effective reinforcement learning method with an adaptively modified probabilistic density function to make the agents adaptable to the environment,
v) an useful method for chaotic neural network to associate the memory patterns in the case that each memory patterns have strong correlation each other,
vi) a memory search model with association by features in chaotic neural network which makes system enable a quick association.
These validity has been examined by examples.
|
