English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

We present a custom implementation of a 2D Convolutional Neural Network (CNN)as a viable application for real-time data selection in high-resolution andhigh-rate particle imaging detectors, making use of hardware acceleration inhigh-end Field Programmable Gate Arrays (FPGAs). To meet FPGA resourceconstraints, a two-layer CNN is optimized for accuracy and latency withKerasTuner, and network \textit{quantization} is further used to minimize thecomputing resource utilization of the network. We use "High Level Synthesis forMachine Learning" (\textit{hls4ml}) tools to test CNN deployment on a XilinxUltraScale+ FPGA, which is a proposed FPGA technology for the front-end readoutsystem of the future Deep Underground Neutrino Experiment (DUNE) far detector.We evaluate network accuracy and estimate latency and hardware resource usage,and comment on the feasibility of applying CNNs for real-time data selectionwithin the proposed DUNE data acquisition system.

Real-time Inference with 2D Convolutional Neural Networks on Field Programmable Gate Arrays for High-rate Particle Imaging Detectors