The automated stopping of a spectral measurement with active learning is proposed.The optimal stopping of the measurement is realised with a stopping criterion based on the upper bound of the posterior average of the ...The automated stopping of a spectral measurement with active learning is proposed.The optimal stopping of the measurement is realised with a stopping criterion based on the upper bound of the posterior average of the generalisation error of the Gaussian process regression.It is revealed that the automated stopping criterion of the spectral measurement gives an approximated X-ray absorption spectrum with sufficient accuracy and reduced data size.The proposed method is not only a proof-of-concept of the optimal stopping problem in active learning but also the key to enhancing the efficiency of spectral measurements for highthroughput experiments in the era of materials informatics.展开更多
基金This work was supported by JST-Mirai Program Grant Numbers JPMJMI19G1 and JPMJMI21G2T.U.acknowledges the support of JSPS KAKENHI Grant Number JP18K13984 and QST President’s Strategic Grant(Exploratory Research).H.H.acknowledges the support of NEDO Grant Number JPNP18002 and JST CREST Grant Number JPMJCR1761+2 种基金This work was carried out under the ISM Cooperative Research Program(H30-J-4302 and 2019-ISMCRP-4206)The XAS experiment was performed under the approval of the Photon Factory Program Advisory Committee(Proposal No.2018MP001)The authors thank Dr.Yasuo Takeichi for the support of the experiments at the Photon Factory.
文摘The automated stopping of a spectral measurement with active learning is proposed.The optimal stopping of the measurement is realised with a stopping criterion based on the upper bound of the posterior average of the generalisation error of the Gaussian process regression.It is revealed that the automated stopping criterion of the spectral measurement gives an approximated X-ray absorption spectrum with sufficient accuracy and reduced data size.The proposed method is not only a proof-of-concept of the optimal stopping problem in active learning but also the key to enhancing the efficiency of spectral measurements for highthroughput experiments in the era of materials informatics.
