摘要
由一名新闻记者兼机器人与机器学习每日新闻编辑-调查人员讨论机器学习的新发现。根据来自德国达姆施塔特的新闻报道，NewsRx记者报道，研究表明，“基于A tomic cluster展开公式，提出了Cu-Zr系统的通用机器学习原子间势(MLIP)[R.Drautz，Phys.Rev.B 99，014104(2019)]。”这项研究的资助者包括德国研究基金会(DFG)，德国研究基金会(DFG)。我们的新闻编辑从技术大学达姆施塔特（TU Darmstadt）的研究中获得了一句话，“通过使用密度泛函理论中广泛的Cu-Zr训练数据，该势描述了整个组成范围内晶体和非晶相的广泛性质。因此，机器学习的原子间势(MLIP)能很好地反映实验相图和非晶结构,并能很好地提高准确度.在玻璃态Cu-Zr样品中发现,与经典的原子间势相比,近程有序度有很大差异,揭示了全二十面体基序在材料中的作用.
Abstract
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News – Investigators discuss new findings in Machine Learning. According to news reporting originating from Darmstadt, German y, by NewsRx correspondents, research stated, “A general purpose machine -learni ng interatomic potential (MLIP) for the Cu-Zr system is presented based on the a tomic cluster expansion formalism [R. Drautz, Phys. Rev. B 99 , 014104 (2019)].” Funders for this research include German Research Foundation (DFG), German Resea rch Foundation (DFG). Our news editors obtained a quote from the research from Technical University Da rmstadt (TU Darmstadt), “By using an extensive set of Cu-Zr training data genera ted withdensity functional theory, this potential describes a wide range of prop erties of crystalline as well as amorphous phases within the whole compositional range. Therefore, the machine learning interatomic potential (MLIP) can reprodu ce the experimental phase diagram and amorphous structure with considerably impr oved accuracy. A massively different short-range order compared to classica inte ratomic potentials is found in glassy Cu-Zr samples, shedding light on the role of the full icosahedral motif in the material.”
NETL
NSTL