%0 Generic
%T Bayesian Flow Networks in Continual Learning
%A Mateusz Pyla
%A Kamil Deja
%A Bartłomiej Twardowski
%A Tomasz Trzcinski
%D 2023
%F Mateusz Pyla2023
%O LAMP
%O exported from refbase (http://158.109.8.37/show.php?record=3972), last updated on Fri, 26 Jan 2024 15:06:46 +0100
%X Bayesian Flow Networks (BFNs) has been recently proposed as one of the most promising direction to universal generative modelling, having ability to learn any of the data type. Their power comes from the expressiveness of neural networks and Bayesian inference which make them suitable in the context of continual learning. We delve into the mechanics behind BFNs and conduct the experiments to empirically verify the generative capabilities on non-stationary data.
%9 miscellaneous
%U https://arxiv.org/abs/2310.12001
%U http://158.109.8.37/files/PDT2023.pdf