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

Abstract

In this paper, we show how to adapt and deploy anomaly detection algorithms based on deep autoencoders, for the unsupervised detection of new physics signatures in the extremely challenging environment of a real-time event selection system at the Large Hadron Collider (LHC). We demonstrate that new physics signatures can be enhanced by three orders of magnitude, while staying within the strict latency and resource constraints of a typical LHC event filtering system. This would allow for collecting datasets potentially enriched with high-purity contributions from new physics processes. Through per-layer, highly parallel implementations of network layers, support for autoencoder-specific losses on FPGAs and latent space based inference, we demonstrate that anomaly detection can be performed in as little as $80$ns using 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 next data-taking campaign of the LHC.

References in corpus (8)

• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• Observation of a new particle in the search for the Standard Model Higgs boson with the ATLAS detector at the LHC
• Observation of a new boson at a mass of 125 GeV with the CMS experiment at the LHC
• Quantized Neural Networks: Training Neural Networks with Low Precision Weights and Activations
• FINN: A Framework for Fast, Scalable Binarized Neural Network Inference
• FPGA-based Accelerators of Deep Learning Networks for Learning and Classification: A Review
• Improving Neural Network Quantization without Retraining using Outlier Channel Splitting
• Accelerated Charged Particle Tracking with Graph Neural Networks on FPGAs

Cited by in corpus (26)

• Anomaly detection in high-energy physics using a quantum autoencoder
• Machine Learning for Anomaly Detection in Particle Physics
• Quantum anomaly detection in the latent space of proton collision events at the LHC
• Deep Generative Models for Detector Signature Simulation: A Taxonomic Review
• Lorentz group equivariant autoencoders
• Anomaly Detection under Coordinate Transformations
• Nanosecond anomaly detection with decision trees and real-time application to exotic Higgs decays
• Non-resonant Anomaly Detection with Background Extrapolation
• FastStamp: Accelerating Neural Steganography and Digital Watermarking of Images on FPGAs
• Unsupervised and lightly supervised learning in particle physics
• Real-Time Zero-Day Intrusion Detection System for Automotive Controller Area Network on FPGAs
• Embedded FPGA Developments in 130nm and 28nm CMOS for Machine Learning in Particle Detector Readout
• Simulation-based Anomaly Detection for Multileptons at the LHC
• Development of a resource-efficient FPGA-based neural network regression model for the ATLAS muon trigger upgrades
• Triggering Dark Showers with Conditional Dual Auto-Encoders
• Semi-supervised permutation invariant particle-level anomaly detection
• da4ml: Distributed Arithmetic for Real-time Neural Networks on FPGAs
• Variational Autoencoders for At-Source Data Reduction and Anomaly Detection in High Energy Particle Detectors
• Nanosecond hardware regression trees in FPGA at the LHC
• BitHEP -- The Limits of Low-Precision ML in HEP
• Tensor Network for Anomaly Detection in the Latent Space of Proton Collision Events at the LHC
• Learning Reduced Representations for Quantum Classifiers
• Anomaly preserving contrastive neural embeddings for end-to-end model-independent searches at the LHC
• It's not a FAD: first results in using Flows for unsupervised Anomaly Detection at 40 MHz at the Large Hadron Collider
• Illuminating all-hadronic final states with a photon: Exotic decays of the Higgs boson to four bottom quarks in vector boson fusion plus gamma at hadron colliders
• Creating Simple, Interpretable Anomaly Detectors for New Physics in Jet Substructure