Search Results for author:
Found 2 papers, 1 papers with code
Designing losses for data-free training of normalizing flows on Boltzmann distributions
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 unbiased estimation of expectations.
Input Similarity from the Neural Network Perspective
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.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
