Aller au contenu. | Aller à la navigation

Outils personnels

Navigation

Voir le monde en interaction

  • Logo CNRS
  • Logo ENSL
  • logo-enssib.jpg
Vous êtes ici : Accueil / Agenda / Séminaires / Talk by Bastien Pasdeloup (EPFL) : A few applications of graph signal processing in machine learning and medicine

Talk by Bastien Pasdeloup (EPFL) : A few applications of graph signal processing in machine learning and medicine

GSP offers new research directions for new domains of application. In particular, we are interested here in machine learning, personalized healthcare and brain comprehension. For each of these domains, we can model a signal of interest as a function on a particular graph. Machine learning exploits the underlying domain of sensored data or social networks, cancerous tissues can be analyzed in terms of a signal of proteins activation on a graph of cells, and brain signals obviously evolve on the human connectome. GSP offers a convenient tool to classify or understand such signals. In this presentation, I will introduce some of my recent/current research to address these problems.
Quand ? Le 05/10/2018,
de 10:00 à 11:00
Où ? M7.101
Ajouter un événement au calendrier vCal
iCal

A few applications of graph signal processing in machine learning and medicine

GSP offers new research directions for new domains of application. In particular, we are interested here in machine learning, personalized healthcare and brain comprehension. For each of these domains, we can model a signal of interest as a function on a particular graph. Machine learning exploits the underlying domain of sensored data or social networks, cancerous tissues can be analyzed in terms of a signal of proteins activation on a graph of cells, and brain signals obviously evolve on the human connectome. GSP offers a convenient tool to classify or understand such signals. In this presentation, I will introduce some of my recent/current research to address these problems.

https://scholar.google.fr/citations?hl=fr&user=dKOgoG4AAAAJ&view_op=list_works&sortby=pubdate