Geometric deep learning : graph convolution for population based Autism prediction

• Auteur / Autrice : Sirine Sboui
• Direction : Faten Chaieb-Chakchouk
• Type : Projet de thèse
• Discipline(s) : Informatique
• Date : Inscription en doctorat le 13/01/2023
• Etablissement(s) : Université Paris-Panthéon-Assas
• Ecole(s) doctorale(s) : École doctorale des sciences économiques et gestion, sciences de l'information et de la communication (Paris)

Résumé

Geometric deep learning specifically deep leaning on graphs has been shown a great results in several domains (natural language processing , medical, video processing) for classification problems. However, modeling data as a graph in medical domain is not always obvious. Recently, many researches are interested on defining a data structure with more than information channel to take advantage of their mix , so they are constructing graphs to apply deep learning on.