activity
20192022
most citedOver-parametrized deep neural networks do not generalize well

9 citations · 14 across the 4 of their papers we have counts for

collaborators

6 papers

math.ST20224 cited

Analysis of the rate of convergence of an over-parametrized deep neural network estimate learned by gradient descent

Michael Kohler, Adam Krzyzak

Estimation of a regression function from independent and identically distributed random variables is considered. The error with integration with respect to the design measure…

stat.ML2020

On the rate of convergence of a deep recurrent neural network estimate in a regression problem with dependent data

Michael Kohler, Adam Krzyzak

A regression problem with dependent data is considered. Regularity assumptions on the dependency of the data are introduced, and it is shown that under suitable structural assumpti…

stat.ML2020

On the rate of convergence of image classifiers based on convolutional neural networks

M. Kohler, A. Krzyzak, B. Walter

Image classifiers based on convolutional neural networks are defined, and the rate of convergence of the misclassification risk of the estimates towards the optimal misclassificati…

math.ST20209 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…

math.ST20191 cited

Analysis of the rate of convergence of neural network regression estimates which are easy to implement

Alina Braun, Michael Kohler, Adam Krzyzak

Recent results in nonparametric regression show that for deep learning, i.e., for neural network estimates with many hidden layers, we are able to achieve good rates of convergence…

stat.ML2019

Estimation of a function of low local dimensionality by deep neural networks

Michael Kohler, Adam Krzyzak, Sophie Langer

Deep neural networks (DNNs) achieve impressive results for complicated tasks like object detection on images and speech recognition. Motivated by this practical success, there is n…