Soutenance de thèse - Aristide Baratin
Some phenomenological investigations in deep learning
The striking success of deep neural networks in machine learning raises a number of theoretical puzzles. For example, why can they generalize to unseen data, despite their capacity to fully memorize the training examples? Such puzzles have been the subject of intense research efforts in the past few years, which combine rigorous analysis of simplified systems with empirical studies of phenomenological properties shown to correlate with generalization. I will present some of my contributions to this line of work. I will highlight and discuss mechanisms that allow large models to prioritize learning 'simple' functions during training and to adapt their capacity to the complexity of the problem.
|Directeur de recherche||Lacoste-Julien, Simon|
|Membre du jury||Courtville, Aaron|
|Examinateur externe||Bruna, Joan (NYU)|
|Représentant du doyen|
Emplacement : Zoom
Pour assister à la conférence, écrivez à Support DIRO avant mercredi 8 juin, 19h.