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

Shruti R. Kulkarni; Aaron Young; Prasanna Date; Narasinga Rao Miniskar; Jeffrey Vetter; Farah Fahim; Benjamin Parpillon; Jennet Dickinson; Nhan Tran; Jieun Yoo; Corrinne Mills; Morris Swartz; Petar Maksimovic; Catherine Schuman; Alice Bean

doi:10.1145/3589737.3605976

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

Shruti R. Kulkarni, Aaron Young, Prasanna Date, Narasinga Rao Miniskar, Jeffrey Vetter, Farah Fahim, Benjamin Parpillon, Jennet Dickinson, Nhan Tran, Jieun Yoo, Corrinne Mills, Morris Swartz, Petar Maksimovic, Catherine Schuman, Alice Bean

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

4 Scopus citations

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 (HL-LHC). 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.

Original language	English
Title of host publication	ICONS 2023 - Proceedings of International Conference on Neuromorphic Systems 2023
Publisher	Association for Computing Machinery
ISBN (Electronic)	9798400701757
DOIs	https://doi.org/10.1145/3589737.3605976
State	Published - Aug 1 2023
Event	2023 International Conference on Neuromorphic Systems, ICONS 2023 - Santa Fe, United States Duration: Aug 1 2023 → Aug 3 2023

Publication series

Name	ACM International Conference Proceeding Series

Conference

Conference	2023 International Conference on Neuromorphic Systems, ICONS 2023
Country/Territory	United States
City	Santa Fe
Period	08/1/23 → 08/3/23

Funding

This work was funded in part by the DOE Office of Science, Advanced Scientific Computing Research (ASCR) program. This research is also funded by the DOE Office of Science Research Program for Microelectronics Codesign (sponsored by ASCR, BES, HEP, NP, and FES) through the Abisko Project with program managers Robinson Pino (ASCR), Hal Finkel (ASCR), and Andrew Schwartz (BES). Personnel were also supported through funding from the National Science Foundation’s Elementary Particle Physics program. This manuscript has been authored by UT-Battelle LLC under contract DE-AC05-00OR22725 with the US Department of Energy (DOE). The US government retains and the publisher, by accepting the article for publication, acknowledges that the US government retains a nonexclusive, paid-up, irrevocable, worldwide license to publish or reproduce the published form of this manuscript, or allow others to do so, for US government purposes. DOE will provide public access to these results of federally sponsored research in accordance with the DOE Public Access Plan (http: //energy.gov/downloads/doe-public-access-plan). This research used resources of the Experimental Computing Laboratory (ExCL) at the Oak Ridge National Laboratory, which is supported by the US Department of Energy (DOE) Office of Science under Contract No. DE-AC05-00OR22725.

Funders	Funder number
Andrew Schwartz
DOE Office of Science Research Program for Microelectronics Codesign
Hal Finkel
National Science Foundation
U.S. Department of Energy
Office of Science	DE-AC05-00OR22725
Basic Energy Sciences
Advanced Scientific Computing Research
UT-Battelle
Higher Education Press

Keywords

evolutionary optimization
neuromorphic computing
spike encoding
spiking neural networks

Access to Document

10.1145/3589737.3605976

Cite this

Kulkarni, S. R., Young, A., Date, P., Rao Miniskar, N., Vetter, J., Fahim, F., Parpillon, B., Dickinson, J., Tran, N., Yoo, J., Mills, C., Swartz, M., Maksimovic, P., Schuman, C., & Bean, A. (2023). On-Sensor Data Filtering using Neuromorphic Computing for High Energy Physics Experiments. In ICONS 2023 - Proceedings of International Conference on Neuromorphic Systems 2023 Article 3 (ACM International Conference Proceeding Series). Association for Computing Machinery. https://doi.org/10.1145/3589737.3605976

@inproceedings{3c124b9eae38479a9baa0b4b8edd65f8,

title = "On-Sensor Data Filtering using Neuromorphic Computing for High Energy Physics Experiments",

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 (HL-LHC). 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.",

keywords = "evolutionary optimization, neuromorphic computing, spike encoding, spiking neural networks",

author = "Kulkarni, {Shruti R.} and Aaron Young and Prasanna Date and {Rao Miniskar}, Narasinga and Jeffrey Vetter and Farah Fahim and Benjamin Parpillon and Jennet Dickinson and Nhan Tran and Jieun Yoo and Corrinne Mills and Morris Swartz and Petar Maksimovic and Catherine Schuman and Alice Bean",

note = "Publisher Copyright: {\textcopyright} 2023 ACM.; 2023 International Conference on Neuromorphic Systems, ICONS 2023 ; Conference date: 01-08-2023 Through 03-08-2023",

year = "2023",

month = aug,

day = "1",

doi = "10.1145/3589737.3605976",

language = "English",

series = "ACM International Conference Proceeding Series",

publisher = "Association for Computing Machinery",

booktitle = "ICONS 2023 - Proceedings of International Conference on Neuromorphic Systems 2023",

}

Kulkarni, SR, Young, A, Date, P , Rao Miniskar, N , Vetter, J, Fahim, F, Parpillon, B, Dickinson, J, Tran, N, Yoo, J, Mills, C, Swartz, M, Maksimovic, P, Schuman, C & Bean, A 2023, On-Sensor Data Filtering using Neuromorphic Computing for High Energy Physics Experiments. in ICONS 2023 - Proceedings of International Conference on Neuromorphic Systems 2023., 3, ACM International Conference Proceeding Series, Association for Computing Machinery, 2023 International Conference on Neuromorphic Systems, ICONS 2023, Santa Fe, United States, 08/1/23. https://doi.org/10.1145/3589737.3605976

On-Sensor Data Filtering using Neuromorphic Computing for High Energy Physics Experiments. / Kulkarni, Shruti R.; Young, Aaron; Date, Prasanna et al.
ICONS 2023 - Proceedings of International Conference on Neuromorphic Systems 2023. Association for Computing Machinery, 2023. 3 (ACM International Conference Proceeding Series).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - On-Sensor Data Filtering using Neuromorphic Computing for High Energy Physics Experiments

AU - Kulkarni, Shruti R.

AU - Young, Aaron

AU - Date, Prasanna

AU - Rao Miniskar, Narasinga

AU - Vetter, Jeffrey

AU - Fahim, Farah

AU - Parpillon, Benjamin

AU - Dickinson, Jennet

AU - Tran, Nhan

AU - Yoo, Jieun

AU - Mills, Corrinne

AU - Swartz, Morris

AU - Maksimovic, Petar

AU - Schuman, Catherine

AU - Bean, Alice

PY - 2023/8/1

Y1 - 2023/8/1

N2 - 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 (HL-LHC). 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.

AB - 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 (HL-LHC). 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.

KW - evolutionary optimization

KW - neuromorphic computing

KW - spike encoding

KW - spiking neural networks

UR - http://www.scopus.com/inward/record.url?scp=85173570591&partnerID=8YFLogxK

U2 - 10.1145/3589737.3605976

DO - 10.1145/3589737.3605976

M3 - Conference contribution

AN - SCOPUS:85173570591

T3 - ACM International Conference Proceeding Series

BT - ICONS 2023 - Proceedings of International Conference on Neuromorphic Systems 2023

PB - Association for Computing Machinery

T2 - 2023 International Conference on Neuromorphic Systems, ICONS 2023

Y2 - 1 August 2023 through 3 August 2023

ER -

Kulkarni SR, Young A, Date P , Rao Miniskar N , Vetter J, Fahim F et al. On-Sensor Data Filtering using Neuromorphic Computing for High Energy Physics Experiments. In ICONS 2023 - Proceedings of International Conference on Neuromorphic Systems 2023. Association for Computing Machinery. 2023. 3. (ACM International Conference Proceeding Series). doi: 10.1145/3589737.3605976

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

Abstract

Publication series

Conference

Funding

Keywords

Access to Document

Other files and links

Fingerprint

Cite this