On-Sensor Data Filtering using Neuromorphic Computing for High Energy Physics Experiments
This work addresses data reduction challenges for high-energy physics experiments at the High Luminosity Large Hadron Collider, representing an incremental improvement in applying neuromorphic computing to a specific domain.
The paper tackled the problem of filtering sensor data in high-energy physics experiments to reduce data transmission by using a neuromorphic spiking neural network (SNN) optimized for hardware deployment. The result was an SNN achieving about 91% signal efficiency with nearly half the parameters of a deep neural network.
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.