Deep-learning top taggers or the end of QCD?

Deep-learning top taggers or the end of QCD?
复制标题

DOI:
10.1007/jhep05(2017)006
复制
发表时间:
2017-01
影响因子:
5.4
通讯作者:
Gregor Kasieczka;T. Plehn;Michael J. Russell;T. Schell
Gregor Kasieczka;T. Plehn;Michael J. Russell;T. Schell
中科院分区:
物理与天体物理2区
文献类型:
--
作者:
Gregor Kasieczka;T. Plehn;Michael J. Russell;T. Schell

文献摘要

被引文献

相似文献

基于卷积神经网络的机器学习可用于大型强子对撞机喷流图像的研究。FAT JET中的TOP标记提供了一个定义良好的框架来建立我们的DeepTop方法,并将其性能与基于QCD的TOP标记器进行比较。我们首先优化了一个网络结构,以便在标准模型生产通道的蒙特卡罗模拟中识别顶夸克。然后,我们使用标准FAT喷气机将其性能与基于多变量QCD的TOP标记器进行比较。我们发现,这两种方法的性能相当,建立卷积网络作为基于多变量假设的顶部标记的一种有前途的新方法。
Machine learning based on convolutional neural networks can be used to study jet images from the LHC. Top tagging in fat jets offers a well-defined framework to establish our DeepTop approach and compare its performance to QCD-based top taggers. We first optimize a network architecture to identify top quarks in Monte Carlo simulations of the Standard Model production channel. Using standard fat jets we then compare its performance to a multivariate QCD-based top tagger. We find that both approaches lead to comparable performance, establishing convolutional networks as a promising new approach for multivariate hypothesis-based top tagging.