Reviews: Approximate Inference Turns Deep Networks into Gaussian Processes

There's some space to improve for the experiments. I think the main contribution of this paper is proposing a method to transform the complicated neural network structure to a nonlinear feature mapping function, so that they can linearly separate the weight and feature mapping. Given the feature mapping, kernels/correlations and posterior distributions over output functions can be explicitly built for BNN (or DNN). Therefore, I would expect to see 1. What does this feature mapping look like? I think the authors show the kernel instead of the mapping itself.