Short bio
Diplôme de l’ENS (Informatique) – Master MVA, École Normale Supérieure de Paris
Thesis title
Efficient parameterization of neural networks for structured data.
Short abstract
My research focuses on guaranteeing that machine learning systems learn to exploit structures present in the data, such as known and approximately known symmetries. Most successful architectures, by design very generic to deal with diverse data inputs (visual, acoustic, textual), fail to do so and thus incur a large computational overhead which could be lightened by exploiting the underlying symmetry. Doing so systematically would yield less resource-hungry architectures with predictive power comparable to the more generic methods.