5 papers
A framework for benchmarking uncertainty in deep regression
Franko Schmähling, Jörg Martin, Clemens Elster
We propose a framework for the assessment of uncertainty quantification in deep regression. The framework is based on regression problems where the regression function is a linear…
About exchanging expectation and supremum for conditional Wasserstein GANs
Jörg Martin
In cases where a Wasserstein GAN depends on a condition the latter is usually handled via an expectation within the loss function. Depending on the way this is motivated, the discr…
Detecting unusual input to neural networks
Jörg Martin, Clemens Elster
Evaluating a neural network on an input that differs markedly from the training data might cause erratic and flawed predictions. We study a method that judges the unusualness of an…
Inspecting adversarial examples using the Fisher information
Jörg Martin, Clemens Elster
Adversarial examples are slight perturbations that are designed to fool artificial neural networks when fed as an input. In this work the usability of the Fisher information for th…
The variation of the posterior variance and Bayesian sample size determination
Jörg Martin, Clemens Elster
We consider Bayesian sample size determination using a criterion that utilizes the first two moments of the expected posterior variance. We study the resulting sample size in depen…