jeandut,github

Hi 👋 I am Jean I work with R&D in topics related to Machine Learning, Computer Vision and Federated Learning applied to HealthCare. I am currently a Lead Research Scientist at Owkin where I connect knowledge from distant hospitals while limiting patient exposure to try to answer long-standing medical questions in Oncology. To this end I use data from multiple modalities such as clinical, histological, survival and genomics. I am a firm believer in open research and published in top-tier venues such as Nature Medicine (1 paper), NeurIPS (2 papers), ICML (1 paper), MICCAI (1 best paper) and ICIP (1 paper) and wrote numerous surveys and technical reports all publicly available ➡️ Link to scholar profile.

In the past few years I've also been:

👨‍🎓 a Ph.D. student in the defense sector working on Object Detection algorithms for Safran (2016-2018)

👨‍💻 an intern at Anametrix applying Data-Science to web-analytics (2015-2016)

👨‍🔬 a summer student at CERN in the CMS department (2013)

👨‍🏫 a student from Supelec (2012-2015)

I recently open-sourced the FLamby repository to provide FL researchers with datasets and tools to come up with better strategies to train Machine Learning in privacy preserving healthcare context. If you are interested in Federated Learning do not hesitate to check it out and to add a star if you like it.

jeandut's Projects

deep-leakage-from-gradients

[NeurIPS 2019] Deep Leakage From Gradients https://arxiv.org/abs/1906.08935

fedeca

Mirror of the code repository associated with the FedECA article

fedml

FedML - The federated learning and analytics library enabling secure and collaborative machine learning on decentralized data anywhere at any scale. Supporting large-scale cross-silo federated learning, cross-device federated learning on smartphones/IoTs, and research simulation. MLOps and App Marketplace are also enabled (https://open.fedml.ai).