The XAI project faces the challenge of requiring AI to be explainable and understandable in human terms and articulates its research along 5 Research Activities
Local to Global Explanations
Algorithms to infer local explanations and their generalization to global ones (post-hoc) and algorithms that are transparent by-design
Causal explanations
languages for expressing explanations in terms of logic rules, with statistical and causal interpretation
Platform and XUI
a XAI platform for sharing experimental dataset and explanation algorithms
Case studies
A repertoire of case studies aimed at in involving also final users
Ethics and Legal
a framework to study the interplay between XAI and ethical and legal dimensions.