摘要
由一名新闻记者-机器人与机器学习的工作人员新闻编辑每日新闻-详细介绍了人工智能ce的数据。根据NewsRx记者从英国利物浦发回的新闻报道，研究表明：“我们提出了几个机器学习(ML)模型，这些模型被开发用来有效地将在银河系中原位形成的恒星与外部形成的恒星以及后来增生的恒星分开。”我们的新闻记者从利物浦约翰摩尔大学的研究中得到一句话：“这些模型，包括人工神经网络KS，决策树和降维技术的例子，都是在一组圆盘状的，从ARTEMIS宇宙学Hydrodynamic Zoom-in模拟中得到的银河系质量星系,我们发现这些模型的输入参数由恒星位置、运动学、化学丰度([Fe/H]和[A/Fe])和光度性质的组合组成,所有类别的Mo Del表现相似,在精度-R Ecall曲线下面积(PR-AUC)分,超出5 kpc的半心半径后为0.6.分。MOD ELS检索到{25$>90}的吸积恒星，样品纯度接近60%，但是通过调整分类阈值可以提高纯度。对于一个模型，我们还在训练中包括了宿主星系的特定属性，以考虑宿主吸积历史的变异性，但这并不能提高性能。
Abstract
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-Data detailed on artificial intelligen ce have been presented. According to news reporting from Liverpool, United Kingd om, by NewsRx journalists, research stated, "We present several machine learning (ML) models developed to efficiently separate stars formed in-situ in Milky Way -type galaxies from those that were formed externally and later accreted." Our news reporters obtained a quote from the research from Liverpool John Moores University: "These models, which include examples from artificial neural networ ks, decision trees and dimensionality reduction techniques, are trained on a sam ple of disc-like, Milky Way-mass galaxies drawn from the ARTEMIS cosmological hy drodynamical zoom-in simulations. We find that the input parameters which provid e an optimal performance for these models consist of a combination of stellar po sitions, kinematics, chemical abundances ([Fe/H] and [a/Fe]) and photometric properties. Mo dels from all categories perform similarly well, with area under the precision-r ecall curve (PR-AUC) scores of 0.6. Beyond a galactocentric radius of 5 kpc, mod els retrieve $>90 {{ \%}}$ of accreted stars, with a sample purity close to 60%, however the p urity can be increased by adjusting the classification threshold. For one model, we also include host galaxy-specific properties in the training, to account for the variability of accretion histories of the hosts, however this does not lead to an improvement in performance."
NETL
NSTL