Coupling algebraic topology theory, formal methods and safety requirements toward a new coverage metric for artificial intelligence models - IRT SystemX Accéder directement au contenu
Article Dans Une Revue Neural Computing and Applications Année : 2022

Coupling algebraic topology theory, formal methods and safety requirements toward a new coverage metric for artificial intelligence models

Faouzi Adjed
Mallek Mziou-Sallami
Frédéric Pelliccia
Mehdi Rezzoug
  • Fonction : Auteur
Lucas Schott
Christophe Bohn
  • Fonction : Auteur
Yesmina Jaafra

Résumé

Safety requirements are among the main barriers to the industrialization of machine learning based on deep learning architectures. In this work, a new metric of data coverage is presented by exploring the algebraic topology theory and the abstract interpretation process. The algebraic topology connects the cloud points of the dataset and the abstract interpretation evaluates the robustness of the model. Thus, the coverage metric evaluates simultaneously the dataset and the robustness, and highlights safe and unsafe areas. We also propose the first complete process to evaluate, in terms of data completeness, the machine learning models by providing a workflow based on the proposed metric and a set of safety requirements applied on autonomous driving. The obtained results provide an interpretable coverage evaluation and a promising line of research in the industrialization of artificial intelligence models. It is important to mention that the proposed metric is not dependent on the specific data. In other terms, it can be applied on 1 to n-dimensional data.
Fichier principal
Vignette du fichier
TDA_AI2_neuralComputingApplication-preprint.pdf (1.43 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03878163 , version 1 (31-03-2023)

Identifiants

Citer

Faouzi Adjed, Mallek Mziou-Sallami, Frédéric Pelliccia, Mehdi Rezzoug, Lucas Schott, et al.. Coupling algebraic topology theory, formal methods and safety requirements toward a new coverage metric for artificial intelligence models. Neural Computing and Applications, 2022, 34 (19), pp.17129-17144. ⟨10.1007/s00521-022-07363-6⟩. ⟨hal-03878163⟩
35 Consultations
94 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More