Uncertainty In Deep Learning-Bayesian CNN

Now we have seen the parameters of a Reparameterization layer. We can start writing the models. First, let's start with how we could create a normal CNN: We will convert this model to a Bayesian Convolutional Neural Network. And note that this model has 98.442 parameters in total. Since Reparameterization layers are different from DenseVariational layers in terms of method parameters, we need to consider this when a writing a custom prior & posterior.