Optimal Neighborhood Contexts in Explainable AI: An Explanandum-Based Evaluation

Over the years, several frameworks have been proposed in the domain of Explainable AI (XAI), however their practical applicability and utility need to be clarified. The neighbourhood contexts are shown to significantly impact the explanations generated by XAI frameworks, thus directly affecting thei...

Popoln opis

Bibliografske podrobnosti

Principais autores:	Urja Pawar, Donna O'Shea, Ruairi O'Reilly, Maebh Costello, Christian Beder
Format:	Artigo
Jezik:	Inglês
Izdano:	IEEE 2024-01-01
Serija:	IEEE Open Journal of the Computer Society
Teme:	Explainable AI healthcare SHAP LIME counterfactuals DiCE ML
Online dostop:	https://ieeexplore.ieee.org/document/10504877/
Oznake:	Označite Brez oznak, prvi označite!