Platform Development of Optimization System based on Active Artificial Neural Network
| Project/Area Number |
23500291
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (C)
|
| Allocation Type | Multi-year Fund |
|---|
| Section | 一般 |
|---|
| Research Field |
Sensitivity informatics/Soft computing
|
|---|
| Research Institution | Sendai National College of Technology |
|---|
Principal Investigator |
|
|---|
| Co-Investigator(Kenkyū-buntansha) |
NAKAJIMA Koji 東北大学, 電気通信研究所, 教授 (60125622)
|
|---|
| Project Period (FY) |
2011 – 2013
|
| Project Status |
Completed (Fiscal Year 2013)
|
| Budget Amount *help |
¥5,200,000 (Direct Cost: ¥4,000,000、Indirect Cost: ¥1,200,000)
Fiscal Year 2013: ¥1,170,000 (Direct Cost: ¥900,000、Indirect Cost: ¥270,000)
Fiscal Year 2012: ¥1,170,000 (Direct Cost: ¥900,000、Indirect Cost: ¥270,000)
Fiscal Year 2011: ¥2,860,000 (Direct Cost: ¥2,200,000、Indirect Cost: ¥660,000)
|
|---|
| Keywords | ニューラルネットワーク / 組合せ最適化問題 / アクティブ / 負性抵抗 / GUI / 高次結合ニューラルネットワーク / IDモデル / 組み合わせ最適化問題 / IDLモデル / GPGPU / MPIプログラミング |
|---|
| Research Abstract |
The purpose of this research is about a practical system based on Artificial Neural Networks, our results are as follows. To use this network, we can always get a best solution of Travelling Salseman Problem which is a practical and typical one. Moreover, we proposed a DS-net to improve calculation time. 2) To the purpose of applying a parallel computation algorithm, we proposed a modular neural network and we used a GPGPU technique and then we achevied an extensive calculation time reduction. 3) We developed a prototype supportive GUI tool to desinge the neural network system.
|
Report
(4 results)
Research Products
(43 results)
