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 Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

In this paper, we show how to adapt and deploy anomaly detection algorithmsbased on deep autoencoders, for the unsupervised detection of new physicssignatures in the extremely challenging environment of a real-time eventselection system at the Large Hadron Collider (LHC). We demonstrate that newphysics signatures can be enhanced by three orders of magnitude, while stayingwithin the strict latency and resource constraints of a typical LHC eventfiltering system. This would allow for collecting datasets potentially enrichedwith high-purity contributions from new physics processes. Through per-layer,highly parallel implementations of network layers, support forautoencoder-specific losses on FPGAs and latent space based inference, wedemonstrate that anomaly detection can be performed in as little as $80\,$nsusing less than 3% of the logic resources in the Xilinx Virtex VU9P FPGA.Opening the way to real-life applications of this idea during the nextdata-taking campaign of the LHC.

Autoencoders on FPGAs for real-time, unsupervised new physics detection at 40 MHz at the Large Hadron Collider