ACETONE: Predictable Programming Framework for ML Applications in Safety-Critical Systems - Université Toulouse 1 Capitole Accéder directement au contenu
Communication Dans Un Congrès Année : 2022

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

Résumé

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. 2012 ACM Subject Classification Computer systems organization → Real-time systems; Software and its engineering → Software notations and tools
Fichier principal
Vignette du fichier
LIPIcs-ECRTS-2022-3.pdf (1.1 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03707284 , version 1 (28-06-2022)

Identifiants

Citer

Iryna De Albuquerque Silva, Thomas Carle, Adrien Gauffriau, Claire Pagetti. ACETONE: Predictable Programming Framework for ML Applications in Safety-Critical Systems. 24th Euromicro Conference on Real-Time Systems (ECRTS 2022), Jun 2022, Modène, Italy. ⟨10.4230/DARTS.8.1.6⟩. ⟨hal-03707284⟩
211 Consultations
257 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More