Post-Doctoral Research Visit F/M Postdoc in Neural Networks and Computational Neuroscience

The Inria center at Université Côte d'Azur includes 42 research teams and 9 support services. The center’s staff (about 500 people) is made up of scientists of different nationalities, engineers, technicians and administrative staff. The teams are mainly located on the university campuses of Sophia Antipolis and Nice as well as Montpellier, in close collaboration with research and higher education laboratories and establishments (Université Côte d'Azur, CNRS, INRAE, INSERM ...), but also with the regional economic players.

With a presence in the fields of computational neuroscience and biology, data science and modeling, software engineering and certification, as well as collaborative robotics, the Inria Centre at Université Côte d'Azur  is a major player in terms of scientific excellence through its results and collaborations at both European and international levels.

We are looking for a postdoc to join the Interdisciplinary Institutes for Artificial Intelligence 3IA Côte d'Azur, in the beautiful French Riviera, to work with 3IA Chair Emanuele Natale on problems at the interface of machine learning and computational neuroscience. The candidate will be part of the COATI joint team between INRIA d'Université Côte d'Azur and the I3S Laboratory.

Depending on the candidate's interests, the research topic will be tailored to one of the following directions:

• Sparsity and Structure in Neural Networks. We are interested in understanding the role of topology in artificial neural networks at a fundamental level. To this end, we have investigated the Strong Lottery Ticket Hypothesis [NFG+24], [dCDN23], [dCDG+23], [dNV22], which states that random neural networks can be pruned to approximate a large class of functions without changing the initial weights. We are also interested in Neural Combinatorial Optimization, where we investigate the use of graph neural networks to solve graph and combinatorial problems, such as approximating centrality measures or performing network alignment.
• Computational Neuroscience. We are interested in developing new tools to understand the nervous system and to explore theories behind neural phenomena. As for developing new tools, we have been working on network alignment algorithms [FCC+21] and network statistical models [RDN24], and we are currently working on GNN-based alignment algorithms to compare connectomes across different species. As for the theoretical side, we are interested in various fundamental questions, including —but not limited to— models of evolution of the brain connectivity structure.

For inquiries on possible research topics, please send an email to emanuèle.natale@univ-cotedazur.fr.

References

• [dCDG+23] Arthur Carvalho Walraven da Cunha, Francesco D’Amore, Frédéric Giroire, Hicham Lesfari, Emanuele Natale, and Laurent Viennot. Revisiting the random subset sum problem. In Inge Li Gørtz, Martin Farach-Colton, Simon J. Puglisi, and Grzegorz Herman, editors, 31st Annual European Symposium on Algorithms, ESA 2023, September 4-6, 2023, Amsterdam, The Netherlands, volume 274 of LIPIcs, pages 37:1–37:11. Schloss Dagstuhl - Leibniz-Zentrum für Informatik, 2023.
• [dCDN23] Arthur da Cunha, Francesco D’Amore, and Natale, Emanuele. Polynomially Over-Parameterized Convolutional Neural Networks Contain Structured Strong Winning Lottery Tickets. In Thirty-Seventh Conference on Neural Information Processing Systems, November 2023.
• [dNV22] Arthur da Cunha, Natale, Emanuele, and Laurent Viennot. Proving the Strong Lottery Ticket Hypothesis for Convolutional Neural Networks. In ICLR 2022 - 10th International Conference on Learning Representations, Virtual, France, April 2022.
• [FCC+21] Matteo Frigo, Emilio Cruciani, David Coudert, Rachid Deriche, Natale, Emanuele, and Samuel Deslauriers-Gauthier. Network Alignment and Similarity Reveal Atlas-Based Topological Differences in Structural Connectomes. Network Neuroscience, 5(3):711–733, September 2021.
• [NFG+24] Natale, Emanuele, Davide Ferre’, Giordano Giambartolomei, Frédéric Giroire, and Frederik Mallmann-Trenn. On the Sparsity of the Strong Lottery Ticket Hypothesis. In The Thirty-eighth Annual Conference on Neural Information Processing Systems, September 2024.
• [RDN24] Aurora Rossi, Samuel Deslauriers-Gauthier, and Natale, Emanuele. On Null Models for Temporal Small-Worldness in Brain Dynamics. Network Neuroscience (Cambridge, Mass.), 8(2):377–394, 2024.

To be discussed with the supervisor at the time of the candidate's skills assessment and agreement on the main project that will be pursued.

Technical skills and level required :

Languages :

Relational skills :

Other valued appreciated :

• Subsidized meals
• Partial reimbursement of public transport costs
• Leave: 7 weeks of annual leave + 10 extra days off due to RTT (statutory reduction in working hours) + possibility of exceptional leave (sick children, moving home, etc.)
• Possibility of teleworking and flexible organization of working hours
• Professional equipment available (videoconferencing, loan of computer equipment, etc.)
• Social, cultural and sports events and activities
• Access to vocational training
• Contribution to mutual insurance (subject to conditions)

Gross Salary : 2788 € per month.