Skip to main content
OSTI.GOVU.S. Department of Energy Office of Scientific and Technical Information
U.S. Department of Energy
Office of Scientific and Technical Information
 

Reliable edge machine learning hardware for scientific applications

Conference ·
 [1];  [1];  [1];  [1];  [1];  [2];  [2];  [2];  [2];  [2];  [2];  [3];  [3];  [3];  [4];  [4];  [5];  [5]
  1. Fermilab
  2. UC, San Diego
  3. UC, Berkeley, Eng. Coll.; LBNL, Berkeley
  4. MIT
  5. Drexel U.
+ Show Author Affiliations
Extreme data rate scientific experiments create massive amounts of data that require efficient ML edge processing. This leads to unique validation challenges for VLSI implementations of ML algorithms: enabling bit-accurate functional simulations for performance validation in experimental software frameworks, verifying those ML models are robust under extreme quantization and pruning, and enabling ultra-fine-grained model inspection for efficient fault tolerance. We discuss approaches to developing and validating reliable algorithms at the scientific edge under such strict latency, resource, power, and area requirements in extreme experimental environments. We study metrics for developing robust algorithms, present preliminary results and mitigation strategies, and conclude with an outlook of these and future directions of research towards the longer-term goal of developing autonomous scientific experimentation methods for accelerated scientific discovery.
Research Organization:
Fermi National Accelerator Laboratory (FNAL), Batavia, IL (United States)
Sponsoring Organization:
USDOE Office of Science (SC), High Energy Physics (HEP) (SC-25)
DOE Contract Number:
AC02-07CH11359
OSTI ID:
2396941
Report Number(s):
FERMILAB-CONF-24-0116-CSAID; arXiv:2406.19522; oai:inspirehep.net:2795937
Country of Publication:
United States
Language:
English

References (8)

Fast inference of deep neural networks in FPGAs for particle physics journal July 2018
A Reconfigurable Neural Network ASIC for Detector Front-End Data Compression at the HL-LHC journal August 2021
Applications and Techniques for Fast Machine Learning in Science journal April 2022
The CMS experiment at the CERN LHC journal August 2008
PyHessian: Neural Networks Through the Lens of the Hessian conference December 2020
Automatic heterogeneous quantization of deep neural networks for low-latency inference on the edge for particle detectors journal June 2021
Performance of the CMS Level-1 trigger in proton-proton collisions at √ s = 13 TeV journal October 2020
FKeras: A Sensitivity Analysis Tool for Edge Neural Networks journal May 2024

Similar Records

Related Subjects