| About this Abstract |
| Meeting |
MS&T24: Materials Science & Technology
|
| Symposium
|
Frontiers of Machine Learning on Materials Discovery
|
| Presentation Title |
Variable Selection for Small-Scale Chemical Experimental Data Based on Bayesian Inference |
| Author(s) |
Yasuhiko Igarashi, Yuki Namiuchi, Koki Obinata, Kan Hatakeyama, Yuya Oaki, Masato Okada |
| On-Site Speaker (Planned) |
Yasuhiko Igarashi |
| Abstract Scope |
Application of data-scientific approaches to conventional sciences, such as materials informatics (MI), has attracted much interest toward data-driven research. However, sufficient big data is not always prepared to apply to machine learning. If small data is effectively utilized with a data-scientific approach, research activities can be accelerated without energy, resource, and cost consumption. This presentation focuses on MI for small data, a recent concept for application of small data, with introduction of model cases, such as control of exfoliation processes to obtain 2D materials. In this presentation, a linear regression model with confidence level is constructed based on Bayesian inference in the analysis of small data. We will also present the analysis of small data combined with the use of recent large-scale language models by Bayesian inference, which can incorporate prior knowledge. The present MI for small data opens potentials of small-data-driven chemistry and materials science. |