| Project/Area Number |
17K19971
|
|---|
| Research Category |
Grant-in-Aid for Challenging Research (Exploratory)
|
| Allocation Type | Multi-year Fund |
|---|
| Research Field |
Information science, computer engineering, and related fields
|
|---|
| Research Institution | Nagoya Institute of Technology |
|---|
Principal Investigator |
TSUMURA Tomoaki 名古屋工業大学, 工学(系)研究科(研究院), 教授 (00335233)
|
|---|
| Project Period (FY) |
2017-06-30 – 2020-03-31
|
| Project Status |
Completed (Fiscal Year 2019)
|
| Budget Amount *help |
¥6,240,000 (Direct Cost: ¥4,800,000、Indirect Cost: ¥1,440,000)
Fiscal Year 2019: ¥1,950,000 (Direct Cost: ¥1,500,000、Indirect Cost: ¥450,000)
Fiscal Year 2018: ¥2,210,000 (Direct Cost: ¥1,700,000、Indirect Cost: ¥510,000)
Fiscal Year 2017: ¥2,080,000 (Direct Cost: ¥1,600,000、Indirect Cost: ¥480,000)
|
|---|
| Keywords | 計算再利用 / Approximate Computing / 近似計算 / 畳み込みニューラルネットワーク / 機械学習 |
|---|
| Outline of Final Research Achievements |
In this study, we aimed to design a common platform for Approximate Computing. We confirmed the availability of this platform on large-scale data processing, such as image processing and machine learning. Especially for convolutional neural networks (CNNs), we show that the computational complexity can be significantly reduced with our method. In addition, we also studied the configuration and implementation of the hardware of the computing platform. We designed it based on a super-scalar processor and evaluated its speed and power consumption. In addition, we proposed a method to reduce power consumption of the platform and confirmed its efficacy by simulation.
|
| Academic Significance and Societal Importance of the Research Achievements |
本申請研究は，Approximate Computing（近似計算）の統一的適用手法の発見，および，可用性の高い近似計算基盤の実現を目指して研究を行った．今後の発展が期待されている科学技術分野は，その多くが，ビッグデータマイニング，機械学習，コンピュータビジョンなど，大規模データの高速処理が必要とされるものであることから，計算量自体を削減することに対する要求は大きく，これまで検討すらされていなかったこの「統一的な近似計算基盤」に関して検討を行ったことは，広きにわたる学術分野・産業の発展につながることが期待できる．
|
