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.

I'm trying to write a Kernel Density Estimation algorithm in Tensorflow. Later, when trying to predict the likelihood of a data point with respect to the model fitted above, for each data point I am evaluating, I am summing together the probability given by each of the kernels above: tf.reduce_sum([kernel._prob(X) for kernel in self.kernels], This approach only works when X is a numpy array, as TF doesn't let you iterate over a Tensor. My question is whether or not there is a way to make the algorithm above work with X as a tf.Tensor or tf.Variable?