Deep Neural Networks for Physics Analysis on low-level whole-detector data at the LHC
Deep Neural Networks for Physics Analysis on low-level whole-detector data at the LHC
复制标题
DOI：
10.1088/1742-6596/1085/4/042034
复制
发表时间：
2017-11
期刊：
影响因子：
--
通讯作者：
W. Bhimji;S. Farrell;T. Kurth;Michela Paganini;Prabhat;Evan Racah
中科院分区：
文献类型：
--
作者：
W. Bhimji;S. Farrell;T. Kurth;Michela Paganini;Prabhat;Evan Racah
最近有相当多的活动将深度卷积神经网络（CNN）应用于粒子物理实验的数据。目前ATLAS/CMS的方法主要集中在量热计的一个子集上，并用于识别物体或特定的粒子类型。我们探索的方法，使用整个量热计，结合跟踪信息，直接进行物理分析：即分类事件作为已知的物理背景或新的物理信号。我们使用现有的RPV超对称分析作为案例研究，并在多通道，高分辨率稀疏图像上探索CNN：应用于NERSC科里超级计算机上的GPU和多节点CPU架构（包括Knights Landing（KNL）Xeon Phi节点）。我们将我们的方法的统计性能与从当前物理分析中选择的高级物理变量以及在这些变量上训练的浅层分类器进行了比较。我们还比较了CPU（扩展到多个KNL节点）和GPU实现的解决方案性能。
There has been considerable recent activity applying deep convolutional neural nets (CNNs) to data from particle physics experiments. Current approaches on ATLAS/CMS have largely focussed on a subset of the calorimeter, and for identifying objects or particular particle types. We explore approaches that use the entire calorimeter, combined with track information, for directly conducting physics analyses: i.e. classifying events as known-physics background or new-physics signals. We use an existing RPV-Supersymmetry analysis as a case study and explore CNNs on multi-channel, high-resolution sparse images: applied on GPU and multi-node CPU architectures (including Knights Landing (KNL) Xeon Phi nodes) on the Cori supercomputer at NERSC. We compare statistical performance of our approaches with selections on high-level physics variables from the current physics analyses, and shallow classifiers trained on those variables. We also compare time-to-solution performance of CPU (scaling to multiple KNL nodes) and GPU implementations.