Formal description of ML models for unambiguous implementation - Certifiability of multi and many-cores architectures Access content directly
Conference Papers Year : 2023

Formal description of ML models for unambiguous implementation

Abstract

Implementing deep neural networks in safety critical systems, in particular in the aeronautical domain, will require to offer adequate specification paradigms to preserve the semantics of the trained model on the final hardware platform. We propose to extend the nnef language in order to allow traceable distribution and parallelisation optimizations of a trained model. We show how such a specification can be implemented in cuda on a Xavier platform.
Fichier principal
Vignette du fichier
main.pdf (320.05 Ko) Télécharger le fichier
Origin Files produced by the author(s)

Dates and versions

hal-04167435 , version 1 (20-07-2023)
hal-04167435 , version 2 (17-06-2024)

Identifiers

Cite

Adrien Gauffriau, Iryna De Albuquerque Silva, Claire Pagetti. Formal description of ML models for unambiguous implementation. 12th European Congress on Embedded Real Time Software and Systems (ERTS 2024), Jun 2024, Toulouse, France. ⟨hal-04167435v2⟩
26 View
45 Download

Altmetric

Share

Gmail Mastodon Facebook X LinkedIn More