En poursuivant votre navigation sur ce site, vous acceptez le dépôt de cookies dans votre navigateur. (En savoir plus)
Portail > Offres > Offre UMR5505-CHLBOU-013 - Post-doctorant (H/F) en machine learning pour analyse IRMf

Post-doc in machine learning for fMRI analysis

This offer is available in the following languages:
Français - Anglais

Assurez-vous que votre profil candidat soit correctement renseigné avant de postuler. Les informations de votre profil complètent celles associées à chaque candidature. Afin d’augmenter votre visibilité sur notre Portail Emploi et ainsi permettre aux recruteurs de consulter votre profil candidat, vous avez la possibilité de déposer votre CV dans notre CVThèque en un clic !

Faites connaître cette offre !

General information

Reference : UMR5505-CHLBOU-013
Workplace : TOULOUSE
Date of publication : Monday, February 11, 2019
Type of Contract : FTC Scientist
Contract Period : 36 months
Expected date of employment : 1 April 2019
Proportion of work : Full time
Remuneration : 2 530 euros bruts per month
Desired level of education : PhD
Experience required : Indifferent


IRIT and CERCO are looking for a highly motivated post-doctoral researcher to work on an ANR project (AI-REPS), in order to study which brain areas support linear operations on a variety of complex semantic constructs: faces (WP1), words (WP2), and sentences (WP3). The fMRI data will be analyzed with multivariate pattern analysis (MVPA) and Deep Learning (DL) methods, which we have already successfully applied several times.


Each WP will comprise two fMRI experiments:
1) A large stimulus set will be obtained by randomly sampling the latent space of the computational models, and Representational Similarity Analysis (RSA) will allow us to test for a potential isomorphism between brain-based and computer-based representations;
2) Several stimuli will be created by adding or subtracting a scaled version of a given feature vector (either a pre-defined vector or a random vector obtained as the difference between two arbitrary stimuli) to a sample point in the latent space. This will provide a rigorous test of linearity of representations for each brain region.
The post-doc will also contribute to the supervision of PhD and Masters students and participate in the lab life.


The potential applicant will have:
- PhD (Cognitive sciences, Neuroscience, Computational Neuroscience, Machine Learning, or Computer science/engineering) with a strong interest in neuroscience and good quantitative/computational skills.
- Prior experience with fMRI analysis and/or Deep Learning methods (Keras, Tensorflow), as assessed by a solid publication record in the relevant international journals or conferences
- Experience in MatLab and/or Python programming is required; experience with scripting languages working in a Linux environment is strongly desired.
- Demonstrated ability to write technical reports and high-impact scientific publications, and to present his/her research work to audiences from specialists to the general public.
- Fluency in English
- Creativity with problem solving would be a plus.

Work Context

Based at the IRIT lab with a joint appointment at the CerCo lab, Toulouse.

We talk about it on Twitter!