arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2107.00656cs.LGastro-ph.IMhep-phnucl-thphysics.data-anstat.ML
收藏

基础物理学中深度学习的共享数据和算法

Shared Data and Algorithms for Deep Learning in Fundamental Physics

Universität Hamburg(汉堡大学);RWTH Aachen University(亚琛工业大学);Ludwig Maximilians University Munich(慕尼黑大学);Frankfurt Institute for Advanced Studies(法兰克福高等研究院);Universität Heidelberg(海德堡大学)
Lisa Benato, Erik Buhmann, Martin Erdmann, Peter Fackeldey, Jonas Glombitza, Nikolai Hartmann, Gregor Kasieczka, William Korcari, Thomas Kuhr, Jan Steinheimer, … 展开作者

Lisa Benato, Erik Buhmann, Martin Erdmann, Peter Fackeldey, Jonas Glombitza, Nikolai Hartmann, Gregor Kasieczka, William Korcari, Thomas Kuhr, Jan Steinheimer, Horst Stöcker, Tilman Plehn, Kai Zhou

摘要:

我们介绍了一个Python包,它提供了对基础物理研究(包括粒子物理学、天体粒子物理学和强子)和核物理学数据集的简单统一访问,用于监督机器学习研究。这些数据集包括强子顶夸克,宇宙射线诱导的空气簇射,强子物质的相变和发电机水平的历史。虽然来自多个基础物理学科的公共数据集已经存在,但通用接口和提供的参考模型简化了基础物理学中跨学科机器学习和迁移学习的未来工作。我们讨论了设计和结构,并列出了如何提交额外的数据集以供纳入。作为示范应用,我们提出了一个简单而灵活的基于图的神经网络架构,可以很容易地应用于广泛的监督学习任务。我们表明,我们的方法在所有数据集上达到了接近专用方法的性能。为了简化对各种问题的适应,我们提供了易于遵循的指令,说明如何构建与基础物理相关的数据结构的基于图形的表示,并提供其中几个的代码实现。我们提出的方法和所有参考算法的实现也提供。

英文摘要:

We introduce a Python package that provides simply and unified access to a collection of datasets from fundamental physics research - including particle physics, astroparticle physics, and hadron- and nuclear physics - for supervised machine learning studies. The datasets contain hadronic top quarks, cosmic-ray induced air showers, phase transitions in hadronic matter, and generator-level histories. While public datasets from multiple fundamental physics disciplines already exist, the common interface and provided reference models simplify future work on cross-disciplinary machine learning and transfer learning in fundamental physics. We discuss the design and structure and line out how additional datasets can be submitted for inclusion. As showcase application, we present a simple yet flexible graph-based neural network architecture that can easily be applied to a wide range of supervised learning tasks. We show that our approach reaches performance close to dedicated methods on all datasets. To simplify adaptation for various problems, we provide easy-to-follow instructions on how graph-based representations of data structures, relevant for fundamental physics, can be constructed and provide code implementations for several of them. Implementations are also provided for our proposed method and all reference algorithms.

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。

↑