Deep learning methods for efficient adaptive neuroprosthetics H/F

Vacancy details

General information

Organisation

The French Alternative Energies and Atomic Energy Commission (CEA) is a key player in research, development and innovation in four main areas :
• defence and security,
• nuclear energy (fission and fusion),
• technological research for industry,
• fundamental research in the physical sciences and life sciences.

Drawing on its widely acknowledged expertise, and thanks to its 16000 technicians, engineers, researchers and staff, the CEA actively participates in collaborative projects with a large number of academic and industrial partners.

The CEA is established in ten centers spread throughout France
  

Reference

2025-37554  

Description de l'unité

Au sein de l'Institut CEA-List, le département des systèmes et circuits numériques intégrés (DSCIN) a pour ambition de faire le lien entre la technologie et l'algorithme en tirant partie de compétences sur le continuum numérique : de la conception matérielle (électronique et microélectronique) à l'optimisation algorithmique en passant par la prise en compte architecturale (de systèmes embarqués ou de serveurs) tout en adressant un large spectre applicatif (cybersécurité, internet des objets, calcul haute performance, intelligence artificielle, technologies émergentes…).

Position description

Category

Health

Contract

Postdoc

Job title

Deep learning methods for efficient adaptive neuroprosthetics H/F

Subject

We are looking for a researcher to join a project to help understanding human brain mechanisms of re-learning and optimize recuperation process after a stroke. More precisely, the objective is to develop deep learning algorithms (convolutional neural networks, recurrent networks, attention-based layers, etc.) as in to define the most effective learning sequence (e.g., from the simplest to the most complex) in terms of performance (accuracy and training duration), in order to propose the best relearning protocol by guiding the neuroplasticity process in the patient. Curriculum learning techniques will be combined with incremental learning algorithms to define the optimal learning sequences in an artificial neural network, which will then be translated to humans.

Contract duration (months)

24

Job description

We are looking for a highly motivated postdoctoral researcher to join a project to help understanding human brain mechanisms of re-learning and optimize recuperation process after a stroke.

More precisely, the objective is to develop deep learning algorithms (convolutional neural networks, recurrent networks, attention-based layers, etc.) as in [1] to define the most effective learning sequence (e.g., from the simplest to the most complex) in terms of performance (accuracy and training duration), in order to propose the best relearning protocol by guiding the neuroplasticity process in the patient. Curriculum learning techniques [2] will be combined with incremental learning algorithms [3] to define the optimal learning sequences in an artificial neural network, which will then be translated to humans.

In the first stage, we will rely on existing ECoG databases at Clinatec (CEA-Leti) [4], collected from previous clinical trials in paraplegic patients. In the second stage, validation will be carried out on ECoG data from the BCI4STROKE clinical trial involving implanted stroke patients.

Together, these elements represent a significant hope to improve the well-being and autonomy of patients suffering from motor disability after a stroke.

Main responsibilities:

·       The training stage will be performed using the existing ECoG databases, which were collected at Clinatec (CEA-Leti) during previous clinical trials on paraplegic patients.

·       The validation and testing stages will be carried out on the new ECoG datasets collected during the BCI4STROKE clinical trial, which will involve 4 implanted stroke patients.

·       Present findings regularly at consortium meetings, and occasionally at international conferences.

·       Publish results in top-tier peer-reviewed journals.

 

#CEA-LIST ; #Ingénieur ; #Chercheur ; #Research Engineer ; #LI-CB1

Applicant Profile

The candidate should have completed a PhD in Computer Science, Machine Learning, or Signal Processing.

Knowledge and experience in some or all of the following fields will be an asset during the position:

·       Deep learning / Machine Learning

·       Applied mathematics (probability / statistics)

·       Proficiency in software engineering, notably in Python (Tensorflow, PyTorch, with some basic GPU environment knowledge).

·       Applicants should master written and spoken English.

Demonstration of a high degree of autonomy, excellent organizational skills, and very good oral and written communication skills in English.

Motivation to join an interdisciplinary team involving physicians, nurses, MR physicists, researchers from MIND, and to work in project-oriented mode with other partners in the BrainSync consortium.

 

In accordance with the commitments made by the CEA to promote the integration of disabled people, this job is open to all. The CEA proposes arrangements and/or organizational possibilities for the inclusion of disabled workers.

Position location

Site

Grenoble

Job location

France, Auvergne-Rhône-Alpes, Isère (38)

Location

Grenoble

Requester

Position start date

02/03/2026