Hardware-friendly machine learning with integer-parameter regularized learning based on discrete convexity
| Project/Area Number |
25540102
|
|---|
| Research Category |
Grant-in-Aid for Challenging Exploratory Research
|
| Allocation Type | Multi-year Fund |
|---|
| Research Field |
Intelligent informatics
|
|---|
| Research Institution | Osaka University |
|---|
Principal Investigator |
|
|---|
| Co-Investigator(Kenkyū-buntansha) |
山際 伸一 筑波大学, システム情報系, 准教授 (10574725)
|
|---|
| Co-Investigator(Renkei-kenkyūsha) |
NAGANO Kiyohito 群馬大学, 社会情報学部 (20515176)
|
|---|
| Project Period (FY) |
2013-04-01 – 2017-03-31
|
| Project Status |
Completed (Fiscal Year 2016)
|
| Budget Amount *help |
¥3,770,000 (Direct Cost: ¥2,900,000、Indirect Cost: ¥870,000)
Fiscal Year 2015: ¥1,430,000 (Direct Cost: ¥1,100,000、Indirect Cost: ¥330,000)
Fiscal Year 2014: ¥1,430,000 (Direct Cost: ¥1,100,000、Indirect Cost: ¥330,000)
Fiscal Year 2013: ¥910,000 (Direct Cost: ¥700,000、Indirect Cost: ¥210,000)
|
|---|
| Keywords | 機械学習 / 組み込みシステム / 組合せ最適化 |
|---|
| Outline of Final Research Achievements |
We have made a study regularized learning algorithms over integer parameters, and compared several different approaches for that. However, currently, theoretical problems that we did not expected have been revealed, and the computational costs for carrying out those with computers have been revealed. Based on these considerations, as another option, we have considered an approach where learning is performed with structural information among parameters in data. And, we confirmed it could be useful for the purpose of this research project.
|
Report
(5 results)
Research Products
(9 results)
