首页|Researchers' Work from National University of Science & Technology MISiS Focuses on Machine Learning (Training of Machine Learning Potentials for the Modeling of Nucleation In Graphite)
Researchers' Work from National University of Science & Technology MISiS Focuses on Machine Learning (Training of Machine Learning Potentials for the Modeling of Nucleation In Graphite)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-Investigators publish new report on Ma chine Learning. According to news originating from Moscow, Russia, by NewsRx cor respondents, research stated, "The parameterization of machine learning potentia ls (MLP) for precise characterization of the interaction between carbon atoms in graphite and diamond phases is described. The training set consisted of various allotropic forms of carbon and their compounds." Financial support for this research came from Russian Science Foundation (RSF). Our news journalists obtained a quote from the research from the National Univer sity of Science & Technology MISiS, "The MLPs are trained using fo rces, energies, and stress tensors obtained from ab initio simulations. It is sh own that the MLPs can accurately reproduce elastic properties and structural par ameters of carbon phases. However, the MLPs also predict some unphysical behavio r due to the training set limitations and the lack of long-range interactions in the MLPs." According to the news editors, the research concluded: "In spite of these limita tions, MLPs are a promising tool for the accurate characterization of diamond nu cleation in graphite." This research has been peer-reviewed.
MoscowRussiaCarbonCyborgsEmergin g TechnologiesGraphiteMachine LearningMineralsNational University of Sci ence & Technology MISiS
NETL
NSTL
