Annonce en lien avec l’Action/le Réseau : aucun

Laboratoire/Entreprise : Laboratoire d’informatique Fondamentale (LIF) – Institut de Neurosciences de la Timone (INT)
Durée : 2 ans
Contact : thierry.artieres@lif.univ-mrs.fr
Date limite de publication : 2017-06-11

Contexte :
The Machine Learning team (QARMA, https://qarma.lif.univ-mrs.fr/ ) of the Computer Science Lab at Aix-Marseille university and the Institute on Neurosciences of La Timone (INT) are looking for a postdoctoral research associate to join our teams to work on machine learning research applied to neuroscience data and tasks.

The postdoc will joint the QARMA team at LIF. The QARMA team focuses on statistical machine learning. It gathers about ten researchers with complementary skills on signal processing, theoretical and applied machine learning, computer science. They focus on few fundemantal research axis like signal processing and machine learning, machine learning theory, and deep learning and on applied research related to neuroscience and to natural language processing.

This project is research focused and part of the ILCB project (http://www.ilcb.fr/about.html ) which constitutes a major initiative in Cognitive Science that aims to explore the neural basis of human language and communication by studying the components of L&C and proposing unifying models and architectures. The originality and ambition of the ILCB lies in the integration of a wide range of disciplines, methodologies and experimental techniques that all contribute to the description of human language processing and communication (as paradigmatic examples of high-level cognitive functions) in laboratory and naturalistic settings.

Sujet :
Research projects are to be build jointly by the candidate and the QARMA team. It should address deep learning and machine learning questions applied to existing neuroscience problems and data, or be more theoretical with potential links with neuroscience.

In particular we are interested in learning common representation space for handling inter-subject variability, and in enabling transfer to incoming subjects. Research themes could include, but are not limited to :
– Deep learning and representation learning
– Learning from few samples
– Learning on spatio-temporal data
– Multi-view, multi-task, multi-source learning, eventually with missing data
– Learning on graphs or learning from graphs
– Neuroscience insights for machine learning models

Profil du candidat :
Candidates should have a PhD in Computer Science, Mathematics, Electrical Engineering or related field. An established expertise in Machine Learning, Deep learning, Neuroscoentific data is desired with an ability to think of innovative solutions.

Formation et compétences requises :

Specific skills sought after include:
* Experience in machine learning
* Strong interest in deep learning techniques
* Ability to work with large datasets
* Experience with common data science and deep learning toolkits such as scikit-learn, Theano, TensorFlow, Lasagne, Keras, etc.
* Strong interest in the combination of theoretical and experimental research.
* Communicative, enthusiastic and good a team player.

Adresse d’emploi :
CMI, Parc de l’Etoile, Chateau Gombert, 13013, Marseille

Document attaché :