66 citations · 124 across the 22 of their papers we have counts for
Showing 2020 · math.STShow all
3 papers · 2 filters
math.ST2020
On the density estimation problem for uncertainty propagation with unknown input distributions
Sebastian Kersting, Michael Kohler
In this article we study the problem of quantifying the uncertainty in an experiment with a technical system. We propose new density estimates which combine observed data of the te…
math.ST2020★ 10 cited
Statistical theory for image classification using deep convolutional neural networks with cross-entropy loss under the hierarchical max-pooling model
Michael Kohler, Sophie Langer
Convolutional neural networks (CNNs) trained with cross-entropy loss have proven to be extremely successful in classifying images. In recent years, much work has been done to also…
math.ST2020★ 9 cited
Over-parametrized deep neural networks do not generalize well
Michael Kohler, Adam Krzyzak
Recently it was shown in several papers that backpropagation is able to find the global minimum of the empirical risk on the training data using over-parametrized deep neural netwo…