logo
ResearchBunny Logo
Nanosecond anomaly detection with decision trees and real-time application to exotic Higgs decays

Physics

Nanosecond anomaly detection with decision trees and real-time application to exotic Higgs decays

S. T. Roche, Q. Bayer, et al.

Explore how a team of innovative researchers, including S. T. Roche and Q. Bayer, developed an autoencoding algorithm using deep decision trees on FPGA for rapid anomaly detection at the LHC. This groundbreaking system not only detects rare Higgs boson decays with incredible speed but also operates efficiently in resource-limited environments, paving the way for advanced applications in edge AI.

00:00
Playback language: English
Abstract
This paper presents an interpretable autoencoding algorithm implemented with a deep decision tree forest on FPGA for nanosecond anomaly detection. The autoencoder, trained on known Standard Model (SM) processes, is deployed in real-time trigger systems at the Large Hadron Collider (LHC) to detect anomalies such as rare exotic Higgs boson decays. The system achieves 30 ns latency with minimal resource usage, offering low-latency anomaly detection for resource-constrained edge AI applications.
Publisher
Nature Communications
Published On
Apr 25, 2024
Authors
S. T. Roche, Q. Bayer, B. T. Carlson, W. C. Ouligian, P. Serhiayenka, J. Stelzer, T. M. Hong
Tags
autoencoder
anomaly detection
FPGA
Higgs boson
edge AI
deep decision trees
LHC
Listen, Learn & Level Up
Over 10,000 hours of research content in 25+ fields, available in 12+ languages.
No more digging through PDFs, just hit play and absorb the world's latest research in your language, on your time.
listen to research audio papers with researchbunny