3 papers
cs.LG2026
It's Not a Lottery, It's a Race: Understanding How Gradient Descent Adapts the Network's Capacity to the Task
Hannah Pinson
Our theoretical understanding of neural networks is lagging behind their empirical success. One of the important unexplained phenomena is why and how, during the process of trainin…
cs.CV2023
Linear CNNs Discover the Statistical Structure of the Dataset Using Only the Most Dominant Frequencies
Hannah Pinson, Joeri Lenaerts, Vincent Ginis
We here present a stepping stone towards a deeper understanding of convolutional neural networks (CNNs) in the form of a theory of learning in linear CNNs. Through analyzing the gr…
cs.LG2022
Data driven design of optical resonators
Joeri Lenaerts, Hannah Pinson, Vincent Ginis
Optical devices lie at the heart of most of the technology we see around us. When one actually wants to make such an optical device, one can predict its optical behavior using comp…