28 citations · 31 across the 2 of their papers we have counts for
2 papers
cs.LG2023★ 3 cited
Designing losses for data-free training of normalizing flows on Boltzmann distributions
Loris Felardos, Jérôme Hénin, Guillaume Charpiat
Generating a Boltzmann distribution in high dimension has recently been achieved with Normalizing Flows, which enable fast and exact computation of the generated density, and thus…
cs.LG2021★ 28 cited
Input Similarity from the Neural Network Perspective
Guillaume Charpiat, Nicolas Girard, Loris Felardos +1
We first exhibit a multimodal image registration task, for which a neural network trained on a dataset with noisy labels reaches almost perfect accuracy, far beyond noise variance.…