Vous êtes ici : Accueil » Kiosque » Annonce


Mot de passe : 

Mot de passe oublié ?
Détails d'identification oubliés ?


12 janvier 2021

Graph Signal Processing for multimodal Neuroimaging

Catégorie : Post-doctorant

18 months postdoc in Neuroimaging and Machine Learning, using Graph Signal Processing (GSP) for multimodal data fusion. See here : https://partage.imt.fr/index.php/s/xcDAYZ49NELgqqg



IMPORTANT : The present postdoctoral fellowship is funded by the Sustainable Attractivity Strategy of the Brittany Region, with the goal of attracting high profile junior researchers from all over the world, offering exceptional conditions for long-term academic development. To fulfill the criteria, the candidate must have spent a minimum 18 months outside France in the last 3 years.

The BRAIn project at IMT Atlantique (UMR CNRS LabSTICC, T2I3 pole, 2AI team) is seeking a highly qualified young researcher with experience and motivation in Computational Neuroscience and Machine Learning. This position is open by IMT Atlantique Brest (France) within the framework of the MultiGSP (Multimodal Graph Signal Processing) research project. The objective of the MultiGSP project is to exploit the theoretical framework of Graph Signal Processing (GSP) for multimodal data fusion. We use the application framework of Neuroimaging to put in place models, and we aim for a long-term extension to other types of data.

GSP is an expanding research area1 that extends classical analysis methods to non-regular domains, exploiting the topology of the underlying graphs. GSP is therefore a flexible tool to associate signals (i.e. brain activity) to an underlying structure (i.e. brain anatomical networks). The increasing interest that GSP is receiving also results from the powerful correspondence between graph Laplacian eigenvectors and frequency Fourier analysis. GSP represents an ideal yet mostly unexplored framework to integrate multi-modal brain signals, associating structural, electrophysiologic, metabolic and functional information. The selected candidate will collaborate with the other members of the team and their collaborators to develop novel methods based on GSP to efficiently integrate information from different neuroimaging techniques (e.g. Electroencephalography-EEG, functional Magnetic Resonance Imaging- fMRI, Diffusion Weighted Imaging, DWI).

A secondary mission of the Post-Doc will be to contribute to the development of deep learning methods for Neuroimaging, in line with the research axes of the team. IMT Atlantique is a technological university and offers very competitive salary packages, with postdoc wages corresponing to a junior assistant professor level. Successful candidates will also benefits from 49 days of annual paid holidays.

Research Environment

The BRAIn team is a reference for its work at the intersection between signal processing on graphs (Nicolas Farrugia, Vincent Gripon), deep learning (Vincent Gripon, Mathieu Leonardon), and neuroimaging (Giulia Lioi, Nicolas Farrugia), and has already contributed to the emerging field of GSP/Neuroimaging with a series of seminal works.

Within the context of the MultiGSP project, the BRAIn team closely collaborate with the IMAGINE team (Integration of multimodal information for decision making and optimization of therapies interventions) of the LATIM laboratory (François Rousseau).

Applicant Profile

The Ideal applicant should have:

How to apply

Applicants should send their complete application package by email to giulia.lioi@imt-atlantique.fr and nicolas.farrugia@imt-atlantique.fr

This includes:

A PDF version of this call can be found here :



Dans cette rubrique

(c) GdR 720 ISIS - CNRS - 2011-2020.