arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2103.01596hep-phcs.LGhep-exphysics.comp-phstat.ML
收藏

用于ProtoDUNE原始数据去噪的深度学习策略

Deep Learning strategies for ProtoDUNE raw data denoising

Università degli Studi di Milano(米兰大学);INFN Sezione di Milano(意大利国家核物理研究所米兰分部);CERN openlab(欧洲核子研究中心开放实验室)

Marco Rossi, Sofia Vallecorsa

摘要:

在这项工作中,我们研究了不同的基于机器学习的策略,用于对ProtodUNE实验中的原始模拟数据进行去噪。ProtoDUNE探测器由CERN主持,旨在测试和校准DUNE的技术,这是一个即将到来的中微子物理实验。重建工作链包括将数字探测器信号转换为物理高级量。我们解决了重建的第一步,即利用深度学习算法对原始数据进行去噪。我们设计了两种基于图神经网络的架构,旨在增强基本卷积神经网络的感受野。我们基准这种方法对传统算法实现的DUNE合作。我们测试了图神经网络硬件加速器设置的能力,以加快训练和推理过程。

英文摘要:

In this work, we investigate different machine learning-based strategies for denoising raw simulation data from the ProtoDUNE experiment. The ProtoDUNE detector is hosted by CERN and it aims to test and calibrate the technologies for DUNE, a forthcoming experiment in neutrino physics. The reconstruction workchain consists of converting digital detector signals into physical high-level quantities. We address the first step in reconstruction, namely raw data denoising, leveraging deep learning algorithms. We design two architectures based on graph neural networks, aiming to enhance the receptive field of basic convolutional neural networks. We benchmark this approach against traditional algorithms implemented by the DUNE collaboration. We test the capabilities of graph neural network hardware accelerator setups to speed up training and inference processes.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑