66 citations · 124 across the 22 of their papers we have counts for
23 papers
Learning of deep neural network regression estimates using gradient descent with pruning
Michael Kohler, Vincent Molinero Römer, Adam Krzyżak
Estimation of a regression function from independent and identically distributed data is considered. The error with integration with respect to the design variable is used as…
Estimation of a regression function from dependent data by over-parametrized deep neural networks learned by gradient descent
Michael Kohler, Adam Krzyżak, Vincent Molinero Römer
Estimation of a regression function from exponentially -mixing data is considered. The error with integration with respect to the design is used as the error criterion. De…
Analysis of the rate of convergence of an over-parametrized convolutional neural network image classifier learned by gradient descent
Michael Kohler, Adam Krzyzak, Benjamin Walter
Image classification based on over-parametrized convolutional neural networks with a global average-pooling layer is considered. The weights of the network are learned by gradient…
Learning of deep convolutional network image classifiers via stochastic gradient descent and over-parametrization
Michael Kohler, Adam Krzyzak, Alisha Sänger
Image classification from independent and identically distributed random variables is considered. Image classifiers are defined which are based on a linear combination of deep conv…
On the rate of convergence of an over-parametrized Transformer classifier learned by gradient descent
Michael Kohler, Adam Krzyzak
One of the most recent and fascinating breakthroughs in artificial intelligence is ChatGPT, a chatbot which can simulate human conversation. ChatGPT is an instance of GPT4, which i…
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…