arXiv 1902.082762019-02hep-excs.CVcs.LGphysics.data-an

利用CMS开放数据对夸克和胶子的端到端喷注分类

End-to-End Jet Classification of Quarks and Gluons with the CMS Open Data

Carnegie Mellon University（卡内基梅隆大学）；CERN（欧洲核子研究组织）；Brown University（布朗大学）；University of Alabama（阿拉巴马大学）

Michael Andrews, John Alison, Sitong An, Patrick Bryant, Bjorn Burkle, Sergei Gleyzer, Meenakshi Narain, Manfred Paulini, Barnabas Poczos, Emanuele Usai

备注：: 10 pages, 5 figures, 7 tables; v2: published version
发表信息：: Nucl. Instrum. Methods Phys. Res. A 977, 164304 (2020)
DOI：: 10.1016/j.nima.2020.164304

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

摘要：

我们描述了端到端的喷流图像分类器的建设的基础上，模拟低水平的探测器数据来区分夸克与胶子发起的喷流与高保真模拟CMS开放数据。我们强调了精确的空间信息的重要性，并展示了与现有最先进的射流分类器相比的竞争性能。我们进一步推广了端到端的方法，夸克与胶子双喷QCD事件的事件级分类。我们比较了完全端到端的方法，使用手工设计的功能，并证明了端到端的算法是强大的基础事件和堆积的影响。

英文摘要：

We describe the construction of end-to-end jet image classifiers based on simulated low-level detector data to discriminate quark- vs. gluon-initiated jets with high-fidelity simulated CMS Open Data. We highlight the importance of precise spatial information and demonstrate competitive performance to existing state-of-the-art jet classifiers. We further generalize the end-to-end approach to event-level classification of quark vs. gluon di-jet QCD events. We compare the fully end-to-end approach to using hand-engineered features and demonstrate that the end-to-end algorithm is robust against the effects of underlying event and pile-up.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

摘要：

英文摘要：

相关论文