I am currently Research Science Director at Meta Reality Labs in Paris. I work on machine learning technologies to decode surface EMG signals (see paper in Nature). Previously I was research director (DR, HdR) at Inria, leading the MIND Team, known formerly as Parietal. My work is on statistical machine learning, signal and image processing, optimization, scientific computing and software engineering with primary applications in neuroscience and biosignal processing. Before joining Inria, I was an assistant professor for 5 years at Telecom Paris in the signal processing and machine learning department and before I was at the Martinos Center for Biomedical Imaging at Harvard University in Boston. I was also a co-director of the Center for Data Science at Université Paris-Saclay. In 2015, I got an ERC Starting Grant for my project called Signal and Learning Applied to Brain data (SLAB) and in 2019 a grant ANR Chaire on Artificial Intelligence called BrAIN.
See my list of publications.
— The reference Python library for machine learning. I am a co-creator and long-standing core developer.
— A complete package to process EEG and MEG data: forward and inverse modeling, preprocessing, statistics, time-frequency analysis. I am the initial creator and core developer (stepped down as BDFL in 2023).
— Deep learning toolbox for decoding EEG, ECG, and MEG signals using PyTorch.
— Machine learning on multivariate data via the Riemannian geometry of symmetric positive definite matrices. Particularly effective for BCI applications.
— C++ package for low-frequency bio-electromagnetism including the EEG/MEG forward problem. Implements the Symmetric BEM for high-accuracy solutions.
— Sphinx extension that automatically generates example galleries from Python scripts. Widely adopted across the scientific Python ecosystem.