66 citations · 83 across the 2 of their papers we have counts for
3 papers
eess.IV2020★ 66 cited
Integrating uncertainty in deep neural networks for MRI based stroke analysis
Lisa Herzog, Elvis Murina, Oliver Dürr +2
At present, the majority of the proposed Deep Learning (DL) methods provide point predictions without quantifying the models uncertainty. However, a quantification of the reliabili…
cs.LG2020★ 17 cited
Single Shot MC Dropout Approximation
Kai Brach, Beate Sick, Oliver Dürr
Deep neural networks (DNNs) are known for their high prediction performance, especially in perceptual tasks such as object recognition or autonomous driving. Still, DNNs are prone…
stat.ML2020
Deep transformation models: Tackling complex regression problems with neural network based transformation models
Beate Sick, Torsten Hothorn, Oliver Dürr
We present a deep transformation model for probabilistic regression. Deep learning is known for outstandingly accurate predictions on complex data but in regression tasks, it is pr…