Bayesian Circulation Networks in Continuous Studying
Authors: Mateusz Pyla, Kamil Deja, Bartłomiej Twardowski, Tomasz Trzciński
Summary: Bayesian Circulation Networks (BFNs) has been lately proposed as one of the promising course to common generative modelling, having skill to be taught any of the info kind. Their energy comes from the expressiveness of neural networks and Bayesian inference which make them appropriate within the context of continuous studying. We delve into the mechanics behind BFNs and conduct the experiments to empirically confirm the generative capabilities on non-stationary information.
