Conveners
人工智能与应用
- 胜森 孙 (Institute of High Energy Physics)
笔豪 郭
(中国科学院合肥物质科学研究院)
28/06/2024, 14:00
分会报告
Plasma disruption is a very dangerous event for future tokamaks and fusion reactors. Therefore, predicting disruption is crucial for ensuring the safety and performance of reactors. In this study, the features of two deep learning algorithms are integrated to establish a multi-scale hybrid network disruption predictor. Firstly, 43 diagnostic signals are extracted by a convolutional neural...
Libo Liao
(wuzhou univercity)
28/06/2024, 14:15
分会报告
背景介绍 2012年在大型强子对撞机(LHC)上发现希格斯(Higgs)玻色子是粒子物理学界的大事件,该发现不仅补全了标准模型缺失的最后一角,而且开启了粒子物理探索的新篇章。由于WZH三种玻色子(尤其是希格斯玻色子)与新物理现象及新物理规律的联系十分密切,因此精确测量他们的性质,是探索新物理现象和新物理规律的关键手段。强子喷注是WZH三种玻色子最主要的衰变末态,因此喷注的重建(Clustering)和标记(Tagging)算法对实现WZH三种玻色子的精确测量至关重要。本文主要介绍喷注的标记算法。传统喷注标记算法有两种,第一种是基于选择条件和人工变量,第二种是基于传统机器学习算法,比如决策树(Boost Decision Tree,...