Hybrid Argument

The project will examine argumentation structures extracted from ML program behavior to support the conclusions they arrive at, thus enhancing the explainability of data-driven AI.

Another more general thread of this project will be to uncover the links of persuasion, biases, learnability and argumentation, linking with the projects of Loubes and Castet-Renard.

Programmes : IA acceptable, certifiable & collaborative
Thèmes : explicabilité, fair learning

Porteur :
Leïla Amgoud, DR CNRS, IRIT

Contact
amgoud@irit.fr

Site
https://www.irit.fr/~Leila.Amgoud