Work

Active learning algorithm for computational physics

Year: 2020

Type: article

Abstract: The authors propose a machine learning based method for numerical determination of a multi-dimensional function. The method can reduce the sampled points to about 10% compared with uniform sampling and maintain an accuracy of about or less than 1% error.

Source: Physical Review Research

DOI: 10.1103/physrevresearch.2.013287

Authors: Juan Yao, Yadong Wu, Jahyun Koo, Binghai Yan, Hui Zhai

Institutions: Peng Cheng Laboratory, Tsinghua University, Weizmann Institute of Science

Language: English

Topic: Machine Learning in Materials Science

Subfield: Materials Chemistry

Field: Materials Science

Domain: Physical Sciences

Open Access status: gold

Estimated APC paid: $2,625

Funders: Weizmann Institute of Science, National Natural Science Foundation of China, Ministry of Science and Technology of the People's Republic of China