Normalizing Flows [Rezende and Mohamed 2015] are powerful density estimators that have shown to be able to learn complex distributions, e.g., of natural images [Kingma and Dhariwal 2018].| Sven Elflein
This is a blog post about the paper “Restricting the Flow: Information Bottlenecks for Attribution” by Karl Schulz, Leon Sixt, Federico Tombari and Tim Landgraf published at ICLR 2020. Introduction With the current trend to applying Neural Networks to more and more domains, the question on the explainability of these models is getting more attention. While more traditional machine learning approaches like decision trees and Random Forest incorporate some kind of interpretability based on ...| Sven Elflein
The motivation of this blog post is to provide a intuition and a practical guide to train a (simple) diffusion model [Sohl-Dickstein et al. 2015] together with the respective code leveraging PyTorch. If you are interested in a more mathematical description with proofs I can highly recommend [Luo 2022].| Sven Elflein