PT Unknown
AU Mateusz Pyla
   Kamil Deja
   Bartłomiej Twardowski
   Tomasz Trzcinski
TI Bayesian Flow Networks in Continual Learning
PY 2023
AB 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.
ER