Quantum Machine Learning for b-jet charge identification
Quantum Machine Learning for b-jet charge identification
复制标题
用于b-jet电荷识别的量子机器学习
DOI：
10.1007/jhep08(2022)014
复制
发表时间：
2022-08-01
影响因子：
5.4
通讯作者：
Zuliani, Davide
中科院分区：
文献类型：
--
作者：
Gianelle, Alessio;Koppenburg, Patrick;Zuliani, Davide
机器学习算法在强子射流分类问题中发挥了重要作用。应用于大型强子对撞机数据的各种模型表明，仍有改进的余地。在这种情况下，量子机器学习是一种新的几乎未被探索的方法，量子计算的内在特性可以用来利用粒子相关性来提高射流分类性能。在本文中，我们提出了一种全新的方法来识别射流是否包含由b或(b) over bar夸克在产生时刻形成的强子，该方法基于应用于LHCb实验模拟数据的变分量子分类器。使用LHCb模拟训练和评估量子模型。将该方法与深度神经网络模型进行了比较，以评估哪种方法具有更好的性能。
Machine Learning algorithms have played an important role in hadronic jet classification problems. The large variety of models applied to Large Hadron Collider data has demonstrated that there is still room for improvement. In this context Quantum Machine Learning is a new and almost unexplored methodology, where the intrinsic properties of quantum computation could be used to exploit particles correlations for improving the jet classification performance. In this paper, we present a brand new approach to identify if a jet contains a hadron formed by a b or (b) over bar quark at the moment of production, based on a Variational Quantum Classifier applied to simulated data of the LHCb experiment. Quantum models are trained and evaluated using LHCb simulation. The jet identification performance is compared with a Deep Neural Network model to assess which method gives the better performance.