Uncertainty in Deep Learning: Experiments with Bayesian CNN

This is the fifth part of the series Uncertainty In Deep Learning. This post is a follow-up of previous posts. So not every term or layer is explained throughout this post as they were explained in the previous parts. In Part 3, we used DenseVariational layer in order to implement Bayes by Backprop algorithm. This layer accepts kl_weight as the argument and we will see how exactly it effects the model.