Description
Date depot: 1 janvier 1900
Titre: Interpretability for human-friendly machine learning models
Directrice de thèse:
Marie-Jeanne LESOT (LIP6)
Domaine scientifique: Sciences et technologies de l'information et de la communication
Thématique CNRS : Non defini
Resumé:
The main goal of this thesis is to study interpretability and both to propose new frameworks to formally define human-friendly decisions and to apply them to the paradigm of supervised machine learning models and more precisely classification.
Doctorant.e: Laugel Thibault