Constructing theory of dynamical neural networks and its application to dynamic control
Project/Area Number |
20700215
|
Research Category |
Grant-in-Aid for Young Scientists (B)
|
Allocation Type | Single-year Grants |
Research Field |
Sensitivity informatics/Soft computing
|
Research Institution | Kogakuin University |
Principal Investigator |
KANAMARU Takashi 工学院大学, グローバルエンジニアリング学部, 准教授 (10334468)
|
Project Period (FY) |
2008 – 2011
|
Project Status |
Completed (Fiscal Year 2011)
|
Budget Amount *help |
¥4,160,000 (Direct Cost: ¥3,200,000、Indirect Cost: ¥960,000)
Fiscal Year 2011: ¥780,000 (Direct Cost: ¥600,000、Indirect Cost: ¥180,000)
Fiscal Year 2010: ¥1,170,000 (Direct Cost: ¥900,000、Indirect Cost: ¥270,000)
Fiscal Year 2009: ¥1,170,000 (Direct Cost: ¥900,000、Indirect Cost: ¥270,000)
Fiscal Year 2008: ¥1,040,000 (Direct Cost: ¥800,000、Indirect Cost: ¥240,000)
|
Keywords | パルスニューラルネットワーク / 同期 / 学習 / カオス性 / ハードウェア化 / Stochastic Synchrony / 制御回路 / ニューラルネットワーク / カオス / ハードウェア / 回路 / 運動モデル / 振動 / 運動制御 / 強化学習 / パルスによる学習 / 同期抑制 / 二足歩行モデル / ガオス性 |
Research Abstract |
I construct a theory of dynamical neural network theory, and we apply it to dynamic control of robots. I assume that the theory should have properties of synchronization, pulse-based learning, and chaos. We found the relation between network topology and synchronization, and the stability of memory under the change of concentration of acetylcholine. As for the application, we realized the dynamic control of robot arm based on the dynamic movement of human arm.
|
Report
(6 results)
Research Products
(23 results)