License: Creative Commons Attribution 4.0 International license (CC BY 4.0)
When quoting this document, please refer to the following
DOI: 10.4230/LIPIcs.ECRTS.2022.3
URN: urn:nbn:de:0030-drops-163202
URL: https://drops.dagstuhl.de/opus/volltexte/2022/16320/
Go to the corresponding LIPIcs Volume Portal


De Albuquerque Silva, Iryna ; Carle, Thomas ; Gauffriau, Adrien ; Pagetti, Claire

ACETONE: Predictable Programming Framework for ML Applications in Safety-Critical Systems

pdf-format:
LIPIcs-ECRTS-2022-3.pdf (1 MB)


Abstract

Machine learning applications have been gaining considerable attention in the field of safety-critical systems. Nonetheless, there is up to now no accepted development process that reaches classical safety confidence levels. This is the reason why we have developed a generic programming framework called ACETONE that is compliant with safety objectives (including traceability and WCET computation) for machine learning. More practically, the framework generates C code from a detailed description of off-line trained feed-forward deep neural networks that preserves the semantics of the original trained model and for which the WCET can be assessed with OTAWA. We have compared our results with Keras2c and uTVM with static runtime on a realistic set of benchmarks.

BibTeX - Entry

@InProceedings{dealbuquerquesilva_et_al:LIPIcs.ECRTS.2022.3,
  author =	{De Albuquerque Silva, Iryna and Carle, Thomas and Gauffriau, Adrien and Pagetti, Claire},
  title =	{{ACETONE: Predictable Programming Framework for ML Applications in Safety-Critical Systems}},
  booktitle =	{34th Euromicro Conference on Real-Time Systems (ECRTS 2022)},
  pages =	{3:1--3:19},
  series =	{Leibniz International Proceedings in Informatics (LIPIcs)},
  ISBN =	{978-3-95977-239-6},
  ISSN =	{1868-8969},
  year =	{2022},
  volume =	{231},
  editor =	{Maggio, Martina},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/opus/volltexte/2022/16320},
  URN =		{urn:nbn:de:0030-drops-163202},
  doi =		{10.4230/LIPIcs.ECRTS.2022.3},
  annote =	{Keywords: Real-time safety-critical systems, Worst Case Execution Time analysis, Artificial Neural Networks implementation}
}

Keywords: Real-time safety-critical systems, Worst Case Execution Time analysis, Artificial Neural Networks implementation
Collection: 34th Euromicro Conference on Real-Time Systems (ECRTS 2022)
Issue Date: 2022
Date of publication: 28.06.2022
Supplementary Material: Software (ECRTS 2022 Artifact Evaluation approved artifact): https://doi.org/10.4230/DARTS.8.1.6


DROPS-Home | Fulltext Search | Imprint | Privacy Published by LZI