Publication Details
Authors
Yuma Iwasaki, Ryohto Sawada, Valentin Stanev, Masahiko Ishida, Akihiro Kirihara, Yasutomo Omori, Hiroko Someya, Ichiro Takeuchi, Eiji Saitoh & Shinichi Yorozu
Journal
Nature Partner Journal Computational Materials
DOI
https://doi.org/10.1038/s41524-019-0241-9
Online publication date
October 30, 2019
Press release online (in Japanese)
PDF: 451KB
Three requirements of machine learning in materials developments. Good collaboration between machine learning tools and scientists in materials developments requires sparse modeling, prediction accuracy, and interpretability. One type of interpretable machine learning called factorized asymptotic Bayesian inference hierarchical mixture of experts (FAB/HMEs) satisfies all three criteria (From Identification of advanced spin-driven thermoelectric materials via interpretable machine learning)