Understanding Deep Neural Networks Through the Lens of their Non-Linearity
Séminaire Palaisien, ENSAE, Paris, France
Talks and presentations
On Few-Annotation Learning and Non-Linearity in Deep Neural Networks
Séminaire, CMAP, Paris, France
Improving Few-Shot Learning through Multi-task Representation Learning Theory
National Research Group Talk, Vers un apprentissage pragmatique dans un contexte de données visuelles labellisées limitées; GdR ISIS, Paris, France
Vers une meilleure compréhension des méthodes de méta-apprentissage à travers la théorie de l’apprentissage de représentations multi-tâches
National Conference Talk, Conférence sur l'Apprentissage Automatique (CAp) 2021, Saint-Étienne, France
Optimal Transport as a Defense Against Adversarial Attacks
Conference Talk, International Conference on Pattern Recognition (ICPR) 2020, Virtual
Putting Theory to Work: From Learning Bounds to Meta-Learning Algorithms
Conference Workshop talk, NeurIPS 2020 Workshop on Meta-Learning (MetaLearn 2020), Virtual
Vulnerability of Person Re-Identification Models to Metric Adversarial Attacks
Talk, DATAIA Workshop « Safety & AI » 2020, CentraleSupélec, Université Paris-Saclay, France
Vulnerability of Person Re-Identification Models to Metric Adversarial Attacks
Conference Workshop, CVPR 2020 Workshop on Adversarial Machine Learning in Computer Vision, Virtual