4 papers
ResBuilder: Automated Learning of Depth with Residual Structures
Julian Burghoff, Matthias Rottmann, Jill von Conta +3
In this work, we develop a neural architecture search algorithm, termed Resbuilder, that develops ResNet architectures from scratch that achieve high accuracy at moderate computati…
Risk stratification of malignant melanoma using neural networks
Julian Burghoff, Leonhard Ackermann, Younes Salahdine +5
In order to improve the detection and classification of malignant melanoma, this paper describes an image-based method that can achieve AUROC values of up to 0.78 without additiona…
Who breaks early, looses: goal oriented training of deep neural networks based on port Hamiltonian dynamics
Julian Burghoff, Marc Heinrich Monells, Hanno Gottschalk
The highly structured energy landscape of the loss as a function of parameters for deep neural networks makes it necessary to use sophisticated optimization strategies in order to…
Uncertainty Quantification and Resource-Demanding Computer Vision Applications of Deep Learning
Julian Burghoff, Robin Chan, Hanno Gottschalk +4
Bringing deep neural networks (DNNs) into safety critical applications such as automated driving, medical imaging and finance, requires a thorough treatment of the model's uncertai…