التفاصيل البيبلوغرافية
| العنوان: |
Real-Time Inference With 2D Convolutional Neural Networks on Field Programmable Gate Arrays for High-Rate Particle Imaging Detectors |
| المؤلفون: |
Yeon-jae Jwa, Giuseppe Di Guglielmo, Lukas Arnold, Luca Carloni, Georgia Karagiorgi |
| المصدر: |
Frontiers in Artificial Intelligence, Vol 5 (2022) |
| بيانات النشر: |
Frontiers Media S.A., 2022. |
| سنة النشر: |
2022 |
| المجموعة: |
LCC:Electronic computers. Computer science |
| مصطلحات موضوعية: |
data selection, particle imaging, liquid argon time projection chamber, hardware acceleration of deep learning, real-time machine leaning, fast machine vision, Electronic computers. Computer science, QA75.5-76.95 |
| الوصف: |
We present a custom implementation of a 2D Convolutional Neural Network (CNN) as a viable application for real-time data selection in high-resolution and high-rate particle imaging detectors, making use of hardware acceleration in high-end Field Programmable Gate Arrays (FPGAs). To meet FPGA resource constraints, a two-layer CNN is optimized for accuracy and latency with KerasTuner, and network quantization is further used to minimize the computing resource utilization of the network. We use “High Level Synthesis for Machine Learning” (hls4ml) tools to test CNN deployment on a Xilinx UltraScale+ FPGA, which is an FPGA technology proposed for use in the front-end readout system of the future Deep Underground Neutrino Experiment (DUNE) particle detector. We evaluate network accuracy and estimate latency and hardware resource usage, and comment on the feasibility of applying CNNs for real-time data selection within the currently planned DUNE data acquisition system. This represents the first-ever exploration of employing 2D CNNs on FPGAs for DUNE. |
| نوع الوثيقة: |
article |
| وصف الملف: |
electronic resource |
| اللغة: |
English |
| تدمد: |
2624-8212 |
| Relation: |
https://www.frontiersin.org/articles/10.3389/frai.2022.855184/full; https://doaj.org/toc/2624-8212 |
| DOI: |
10.3389/frai.2022.855184 |
| URL الوصول: |
https://doaj.org/article/3b794927b34e495ca995a80b6341ef21 |
| رقم الانضمام: |
edsdoj.3b794927b34e495ca995a80b6341ef21 |
| قاعدة البيانات: |
Directory of Open Access Journals |
Full Text Finder