Empowering the trustworthiness of ML-based critical systems through engineering activities - Archive ouverte HAL Access content directly
Preprints, Working Papers, ... Year :

Empowering the trustworthiness of ML-based critical systems through engineering activities

(1) , (2) , (3) , (4) , (5) , (6)
1
2
3
4
5
6
Juliette Mattioli
Souhaiel Khalfaoui
  • Function : Author
  • PersonId : 768857
  • IdRef : 169958590
Freddy Lecue
  • Function : Author
  • PersonId : 1114750
Henri Sohier
  • Function : Author
  • PersonId : 1054948
Frédéric Jurie

Abstract

This paper reviews the entire engineering process of trustworthy Machine Learning (ML) algorithms designed to equip critical systems with advanced analytics and decision functions. We start from the fundamental principles of ML and describe the core elements conditioning its trust, particularly through its design: namely domain specification, data engineering, design of the ML algorithms, their implementation, evaluation and deployment. The latter components are organized in an unique framework for the design of trusted ML systems.
Fichier principal
Vignette du fichier
2209.15438.pdf (591.73 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-03808323 , version 1 (10-10-2022)

Identifiers

Cite

Juliette Mattioli, Agnes Delaborde, Souhaiel Khalfaoui, Freddy Lecue, Henri Sohier, et al.. Empowering the trustworthiness of ML-based critical systems through engineering activities. 2022. ⟨hal-03808323⟩
31 View
0 Download

Altmetric

Share

Gmail Facebook Twitter LinkedIn More