Work

Towards a Generic Framework for Black-box Explanation Methods (Extended Version)

Year: 2019

Type: report

Abstract: The main goal of this research report 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. We also describe precisely how each method can be expressed in the framework.

Source: HAL

Authors: Henin, Clement, Le Métayer, Daniel

Institutions: École nationale des ponts et chaussées, PRIVATICS: Modèles, architectures et outils pour la protection de la vie privée dans la société de l'information

Language: English

Topic: Explainable Artificial Intelligence (XAI)

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

OpenAlex ID: W2946699132

Cites:

Cited by: 4

Related to: 10