Creation of efficient simultaneous experiments for multiple objectives under Bayesian theory
Project/Area Number |
17K00316
|
Research Category |
Grant-in-Aid for Scientific Research (C)
|
Allocation Type | Multi-year Fund |
Section | 一般 |
Research Field |
Intelligent informatics
|
Research Institution | Yokohama College of Commerce |
Principal Investigator |
|
Co-Investigator(Kenkyū-buntansha) |
斉藤 友彦 湘南工科大学, 工学部, 准教授 (50464798)
松嶋 敏泰 早稲田大学, 理工学術院, 教授 (30219430)
|
Project Period (FY) |
2017-04-01 – 2023-03-31
|
Project Status |
Completed (Fiscal Year 2022)
|
Budget Amount *help |
¥4,680,000 (Direct Cost: ¥3,600,000、Indirect Cost: ¥1,080,000)
Fiscal Year 2019: ¥2,080,000 (Direct Cost: ¥1,600,000、Indirect Cost: ¥480,000)
Fiscal Year 2018: ¥1,300,000 (Direct Cost: ¥1,000,000、Indirect Cost: ¥300,000)
Fiscal Year 2017: ¥1,300,000 (Direct Cost: ¥1,000,000、Indirect Cost: ¥300,000)
|
Keywords | 同時実験 / 線形基底関数モデル / データ収集コスト / ベイズ線形回帰 / 直交計画 / 実験計画法 / 機械学習 / 符号理論 / 直交基底関数モデル / 情報理論 |
Outline of Final Research Achievements |
In this study, we developed a framework that enables the processing of high-dimensional data, and proposed simultaneous experiments for multiple similar objectives that can examine all the factors to be considered in each objective. Since the model of experimental design can also be represented by an orthogonal basis function model in which all parameters are independent, we proposed a new method that uses both the traditional model and the orthogonal basis function model for programming when the number of factors and the dimensionality of parameters to be handled is very large, and clarified its characteristics.
|
Academic Significance and Societal Importance of the Research Achievements |
実験計画法において,複数目的に対して同時実験を行うことができれば,より少ない実験回数,コストでの実験の実施が期待できる.本研究で提案した同時実験により,これまでコスト面で困難と思われていた実験の実施が可能になるため,新たな応用先の開拓が期待できる.また本研究では,実験計画法のモデルを直交基底関数モデルで表現することで,他分野(機械学習分野,信号処理分野など)との関連を明らかにすることができた.これにより,関連する他分野での研究成果も利用可能となるため,学術的な意義も大きい.
|
Report
(7 results)
Research Products
(39 results)