Accelerating Deep Neural Networks for Real-time Data Selection for High-resolution Imaging Particle Detectors
Accelerating Deep Neural Networks for Real-time Data Selection for High-resolution Imaging Particle Detectors
复制标题
DOI：
10.1109/nysds.2019.8909784
复制
发表时间：
2019-06
期刊：
影响因子：
--
通讯作者：
Y. Jwa;G. Di Guglielmo;L. Carloni;G. Karagiorgi
中科院分区：
文献类型：
--
作者：
Y. Jwa;G. Di Guglielmo;L. Carloni;G. Karagiorgi
本文介绍了卷积神经网络在现场可编程门阵列上的自定义实现、优化和性能评估，以加速深度神经网络对大型二维图像输入的推理。目标应用是高分辨率粒子成像探测器的数据选择，特别是液态氩时间投影室探测器，如未来的深地下中微子实验所使用的探测器。基于深度神经网络对DUNE LArTPC模拟原始数据进行分类的优异性能，以及在远程、长期和有限访问操作检测器条件下对节能数据处理的需求，我们激发了这一特殊应用。
This paper presents the custom implementation, optimization, and performance evaluation of convolutional neural networks on field programmable gate arrays, for the purposes of accelerating deep neural network inference on large, two-dimensional image inputs. The targeted application is that of data selection for high-resolution particle imaging detectors, and in particular liquid argon time projection chamber detectors, such as that employed by the future Deep Underground Neutrino Experiment. We motivate this particular application based on the excellent performance of deep neural networks on classifying simulated raw data from the DUNE LArTPC, combined with the need for power-efficient data processing in the case of remote, long-term, and limited-access operating detector conditions.