On-Sensor Data Filtering using Neuromorphic Computing for High Energy Physics Experiments

TL;DR

This paper explores neuromorphic computing with spiking neural networks to efficiently filter sensor data in high energy physics experiments, reducing data volume while maintaining high signal efficiency.

Contribution

It introduces a compact neuromorphic model trained with evolutionary algorithms for data filtering in particle physics, optimizing hardware deployment.

Findings

Achieved 91% signal efficiency

Reduced model size by nearly 50% compared to deep neural networks

Provided insights on data encoding and hyperparameter optimization

Abstract

This work describes the investigation of neuromorphic computing-based spiking neural network (SNN) models used to filter data from sensor electronics in high energy physics experiments conducted at the High Luminosity Large Hadron Collider. We present our approach for developing a compact neuromorphic model that filters out the sensor data based on the particle's transverse momentum with the goal of reducing the amount of data being sent to the downstream electronics. The incoming charge waveforms are converted to streams of binary-valued events, which are then processed by the SNN. We present our insights on the various system design choices - from data encoding to optimal hyperparameters of the training algorithm - for an accurate and compact SNN optimized for hardware deployment. Our results show that an SNN trained with an evolutionary algorithm and an optimized set of hyperparameters obtains a signal efficiency of about 91% with nearly half as many parameters as a deep neural network.