Deep Learning Methods For Efficient Adaptive Neuroprosthetics H/F - CEA

Le CEA est un acteur majeur de la recherche, au service des citoyens, de l'économie et de l'Etat.

Il apporte des solutions concrètes à leurs besoins dans quatre domaines principaux : transition énergétique, transition numérique, technologies pour la médecine du futur, défense et sécurité sur un socle de recherche fondamentale. Le CEA s'engage depuis plus de 75 ans au service de la souveraineté scientifique, technologique et industrielle de la France et de l'Europe pour un présent et un avenir mieux maîtrisés et plus sûrs.

Implanté au coeur des territoires équipés de très grandes infrastructures de recherche, le CEA dispose d'un large éventail de partenaires académiques et industriels en France, en Europe et à l'international.

Les 20 000 collaboratrices et collaborateurs du CEA partagent trois valeurs fondamentales :

- La conscience des responsabilités
- La coopération
- La curiositéWe 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

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.