Skip to content
Research Euranova
  • tracks
    • Asgard
    • Bishop
  • explore
    • About us
    • Collaboration
    • Master thesis
    • Internship
  • contact
  • tracks
    • Asgard
    • Bishop
  • explore
    • About us
    • Collaboration
    • Master thesis
    • Internship
  • contact
×

Muppet: A Modular and Constructive Decomposition for Perturbation-based Explanation Methods

The topic of explainable AI has recently received attention driven by a growing awareness of the need for transparent and accountable AI. In this paper, we propose a novel methodology to decompose any state-of-the-art perturbation-based explainability approach into four blocks. In addition, we provide Muppet: an open-source Python library for explainable AI.

Continue reading
Papers
euranova white

SERVE

Expertise

Business Strategy
Architecture
Engineering
Applied Data Science
DevOps/MLOps
Training

© 2024 Euranova. All Rights Reserved.

Privacy policy
Cookies notice

CRAFT

digazu

CONTACT

Belgium

Axis Parc
Rue Emile Francqui, 4
1435 Mont-Saint-Guibert
+32 10 75 02 00

France

146 Rue Paradis
Le Noilly Paradis
13006 Marseille
+33 491 67 11 29

Tunisia

Zone d’activités Kheireddine
Rue Socrate, 6
Les Berges du Lac 3 – 2015 Tunis

CAREER

Job Offers

Unsolicited Application

Social media

LinkedIn
Instagram
Youtube