Anomaly detection with spiking neural networks for LHC physics
To address the stringent constraints of ultra-low latency, low power consumption, and high computational efficiency in real-time anomaly detection at the LHC trigger level, this work pioneers the application of spiking neural networks (SNNs) to high-energy physics anomaly detection, proposing a lightweight SNN-based autoencoder. Trained and evaluated on the CMS ADC2021 dataset and optimized for FPGA deployment, the model achieves detection performance comparable to conventional ANN autoencoders across all signal models (AUC difference < 0.01), while reducing logic resource utilization by 42%, cutting power consumption by 58%, and achieving sub-microsecond inference latency. This study demonstrates, for the first time, the feasibility of SNNs in particle physics real-time triggering and establishes a scalable neuromorphic hardware-oriented architectural paradigm—laying a foundational technical basis for edge-intelligent trigger systems in next-generation LHC upgrades.