Communication Dans Un Congrès Année : 2025

Partitioning of AI Models for Execution on Mixed Criticality Systems. A Workflow Approach Proposal

Résumé

We anticipate that in dependable edgeAI AI system development, only a subset of AI-inferred classes must be inferred dependably. The implication is a mixed-criticality AI execution environment where critical processing can be treated substantially differently than any non-critical processing from which is follows that the AI model must be partitioned, allowing separation of critical and non-critical AI-execution. There is currently no standard method of achieving and documenting such a state. This paper examines partitioning for mixedcriticality execution.

Fichier principal
Vignette du fichier
safecomp2025_paper_97.pdf (438.92 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
Licence

Dates et versions

hal-05240625 , version 1 (04-09-2025)

Licence

Identifiants

  • HAL Id : hal-05240625 , version 1

Citer

Hans Dermot Doran. Partitioning of AI Models for Execution on Mixed Criticality Systems. A Workflow Approach Proposal. SAFECOMP 2025 Position Paper, Sep 2025, Stockhlom, Sweden. ⟨hal-05240625⟩

Collections

388 Consultations
67 Téléchargements

Partager

  • More