Rapport (Rapport De Recherche) Année : 2019

Towards a Generic Framework for Black-box Explanations of Algorithmic Decision Systems

Résumé

The main goal of this paper is to define a generic framework for black-box explanation methods in order to make it easier to compare and classify different approaches. We focus on two components of this framework, called respectively “Sampling” and “Generation”, which are characterized formally and used to build a taxonomy of explanation methods. This document gives details on how this framework can be used to describe black-box explanation methods found in the literature.

Fichier principal
Vignette du fichier
RR-9276.pdf (876.87 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
Licence
Loading...

Dates et versions

hal-02131174 , version 1 (20-05-2019)
hal-02131174 , version 2 (23-05-2019)
hal-02131174 , version 3 (29-05-2019)
hal-02131174 , version 4 (05-07-2019)
hal-02131174 , version 5 (16-07-2019)

Licence

Identifiants

  • HAL Id : hal-02131174 , version 1

Citer

Clement Henin, Daniel Le Métayer. Towards a Generic Framework for Black-box Explanations of Algorithmic Decision Systems. [Research Report] RR-9276, Inria Grenoble Rhône-Alpes; Ecole des Ponts ParisTech. 2019. ⟨hal-02131174v1⟩
1335 Consultations
1606 Téléchargements

Partager

  • More