Solution and regularization of inverse problems using high-dimensional neural networks
Project/Area Number |
26330284
|
Research Category |
Grant-in-Aid for Scientific Research (C)
|
Allocation Type | Multi-year Fund |
Section | 一般 |
Research Field |
Soft computing
|
Research Institution | Takushoku University |
Principal Investigator |
|
Project Period (FY) |
2014-04-01 – 2018-03-31
|
Project Status |
Completed (Fiscal Year 2017)
|
Budget Amount *help |
¥4,810,000 (Direct Cost: ¥3,700,000、Indirect Cost: ¥1,110,000)
Fiscal Year 2017: ¥910,000 (Direct Cost: ¥700,000、Indirect Cost: ¥210,000)
Fiscal Year 2016: ¥910,000 (Direct Cost: ¥700,000、Indirect Cost: ¥210,000)
Fiscal Year 2015: ¥1,560,000 (Direct Cost: ¥1,200,000、Indirect Cost: ¥360,000)
Fiscal Year 2014: ¥1,430,000 (Direct Cost: ¥1,100,000、Indirect Cost: ¥330,000)
|
Keywords | ニューラルネット / 高次元数 / 逆問題 / 正則化 / 写像問題 / 表面筋電位 / 姿勢推定 / 移動ロボット / ニューラルネットワーク / 四元数 / 複素数 / 生体信号 / 軌道計画 / 3次元空間 / 不良設定性 |
Outline of Final Research Achievements |
The solution and regularization method of inverse problems by the neural network extended to high-dimensional numbers were studied. In addition, the applications of high-dimensional neural network to actual engineering problems were examined. The effectiveness of high-dimensional neural network was shown by the examination of solution and regularization method of inverse problems by computer simulation. Furthermore, the applicability of high-dimensional neural network was clarified by applied research such as the forearm pose estimation using surface electromyography and the motion sensor, and the motion planning of mobile robot, and so on.
|
Report
(5 results)
Research Products
(16 results)