Towards Multi-timescale Online Monitoring of AI Models: Principles and Preliminary Results - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2023

Towards Multi-timescale Online Monitoring of AI Models: Principles and Preliminary Results

Paul-Marie Raffi
  • Fonction : Auteur

Résumé

Online monitoring is an architectural pattern well-known to safety engineers, but it had to be adapted to AI technologies. In this paper, an innovative multi-time scale online monitoring architecture is presented. The main idea is to combine several monitoring timescales - Present- Time Monitoring (PTM), Near-Past Monitoring (NPM), and Near-Future Monitoring (NFM) - on different monitoring assets (inputs, internal states, and outputs of the AI model) to ensure a high anomaly detection rate by design of the online monitor.
Fichier principal
Vignette du fichier
44.pdf (2.14 Mo) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
Licence

Dates et versions

hal-04240929 , version 1 (13-10-2023)

Licence

Identifiants

  • HAL Id : hal-04240929 , version 1

Citer

Fateh Kaakai, Paul-Marie Raffi. Towards Multi-timescale Online Monitoring of AI Models: Principles and Preliminary Results. SafeAI, AAAI’s Workshop on Artificial Intelligence Safety, Feb 2023, Washinghton, DC, United States. ⟨hal-04240929⟩
40 Consultations
42 Téléchargements

Partager

Gmail Mastodon Facebook X LinkedIn More