- 【Updated on May 12, 2025】 Integration of CiNii Dissertations and CiNii Books into CiNii Research
- Trial version of CiNii Research Knowledge Graph Search feature is available on CiNii Labs
- Suspension and deletion of data provided by Nikkei BP
- Regarding the recording of “Research Data” and “Evidence Data”
Establishing a practical learning theory based on the analysis of learning from easy data
-
- Takimoto Eiji
- Principal Investigator
- 九州大学
-
- 畑埜 晃平
- Co-Investigator
- 九州大学
About This Project
- Japan Grant Number
- JP19H04067 (JGN)
- Funding Program
- Grants-in-Aid for Scientific Research
- Funding Organization
- Japan Society for the Promotion of Science
Kakenhi Information
- Project/Area Number
- 19H04067
- Research Category
- Grant-in-Aid for Scientific Research (B)
- Allocation Type
-
- Single-year Grants
- Review Section / Research Field
-
- Basic Section 60010:Theory of informatics-related
- Research Institution
-
- Kyushu University
- Project Period (FY)
- 2019-04-01 〜 2023-03-31
- Project Status
- Completed
- Budget Amount*help
- 16,380,000 Yen (Direct Cost: 12,600,000 Yen Indirect Cost: 3,780,000 Yen)
Research Abstract
機械学習の分野では，優れた理論保証を持つ手法よりも，理論保証の無い／悪い発見的手法の方が，実データに対しては良い性能を示すことが良くある．本研究では，このような理論と実践の乖離現象を，データそのものの学習容易性／複雑性解析を通して解明し，実データに対する学習アルゴリズムの高精度な性能解析技法の開発を目指す．また，学習容易性の解析を通して，データ生成源に関する新しい自然科学的・人文科学的な解釈・知見を与える．
Keywords
Details 詳細情報について
-
- CRID
- 1040282256991679104
-
- Text Lang
- ja
-
- Data Source
-
- KAKEN
- IRDB
