Rapid Inference of Logic Gate Neural Networks for Anomaly Detection in High Energy Physics

TL;DR

This paper introduces a Convolutional Differentiable Logic Gate Neural Network (CLGN) for rapid anomaly detection in high energy physics, demonstrating high performance and FPGA efficiency for real-time data processing at the LHC.

Contribution

The paper presents a novel CLGN model optimized for high-speed inference, with a public implementation and FPGA synthesis showing zero DSP resource usage, advancing real-time physics data analysis.

Findings

CLGN achieves comparable or better performance than traditional neural networks.

FPGA implementation of CLGN uses no DSP resources, enabling efficient deployment.

Demonstrates potential for on-detector, high-speed inference in high energy physics.

Abstract

The increasing data rates and complexity of detectors at the Large Hadron Collider (LHC) necessitate fast and efficient machine learning models, particularly for rapid selection of what data to store, known as triggering. Building on recent work in differentiable logic gates, we present a public implementation of a Convolutional Differentiable Logic Gate Neural Network (CLGN). We apply this to detecting anomalies at the Level-1 Trigger at CMS using public data from the CICADA project. We demonstrate that the CLGN achieves physics performance on par with or superior to conventional quantized neural networks. We also synthesize an LGN for a Field-Programmable Gate Array (FPGA) and show highly promising FPGA characteristics, notably zero Digital Signal Processor (DSP) resource usage. This work highlights the potential of logic gate networks for high-speed, on-detector inference in High Energy Physics and beyond.