
Members
-
Team directorIchiro Takeuchi
-
Research scientistNoriaki Hashimoto
-
Visiting scientistKeiichi Inoue
-
Visiting scientistToru Ujihara
-
Visiting scientistKentaro Kutsukake
-
Visiting scientistHiroyuki Hanada
-
Visiting scientistDuy Vo
-
Junior research associateShuichi Nishino
-
Junior research associateTomohiro Shiraishi
-
Part-time worker IOnur Boyar
-
Part-time worker IXudong Chen
Introduction

In various fields of scientific research, data-driven approaches are enabling the generation of hypotheses, the planning of experiments, and even the discovery of new knowledge, thereby bringing innovation to the researchprocess. At the same time, data-driven research faces challenges such as limited interpretability, susceptibility to bias, and a lack of reproducibility, making it essential to ensure reliability and transparency. In conventional research, systematic practices based on "experimental design" have been established as methodologies for research design—determining which experiments to conduct and how to draw conclusions from their results. The mission of our team is to evolve and advance this framework to adapt to data-driven research, thereby establishing a foundation for "data-driven experimental design," and ensuring the sound development of data-driven science. To achieve this goal, we are developing novel machine learning techniques tailored to scientific research and demonstrating their effectiveness across a range of scientific challenges.
Introduction Video
Poster(s)
- FY2024 Research Results(PDF 3MB) (Japanese version)
- FY2023 Research Results(PDF 557KB) (Japanese version)
- FY2022 Research Results(PDF 2.47MB)(Japanese version)
- FY2021 Research Results(PDF 1.72MB)(Japanese version)
- FY2019 Research Results(PDF 2.1MB) (Japanese version)
- FY2018 Research Results(PDF 3.98MB) (Japanese version)