4 citations · 4 across the 6 of their papers we have counts for
6 papers
Physical knowledge improves prediction of EM Fields
Andrzej Dulny, Farzad Jabbarigargari, Andreas Hotho +3
We propose a 3D U-Net model to predict the spatial distribution of electromagnetic fields inside a radio-frequency (RF) coil with a subject present, using the phase, amplitude, and…
GrINd: Grid Interpolation Network for Scattered Observations
Andrzej Dulny, Paul Heinisch, Andreas Hotho +1
Predicting the evolution of spatiotemporal physical systems from sparse and scattered observational data poses a significant challenge in various scientific domains. Traditional me…
TaylorPDENet: Learning PDEs from non-grid Data
Paul Heinisch, Andrzej Dulny, Anna Krause +1
Modeling data obtained from dynamical systems has gained attention in recent years as a challenging task for machine learning models. Previous approaches assume the measurements to…
DynaBench: A benchmark dataset for learning dynamical systems from low-resolution data
Andrzej Dulny, Andreas Hotho, Anna Krause
Previous work on learning physical systems from data has focused on high-resolution grid-structured measurements. However, real-world knowledge of such systems (e.g. weather data)…
Do Different Deep Metric Learning Losses Lead to Similar Learned Features?
Konstantin Kobs, Michael Steininger, Andrzej Dulny +1
Recent studies have shown that many deep metric learning loss functions perform very similarly under the same experimental conditions. One potential reason for this unexpected resu…
NeuralPDE: Modelling Dynamical Systems from Data
Andrzej Dulny, Andreas Hotho, Anna Krause
Many physical processes such as weather phenomena or fluid mechanics are governed by partial differential equations (PDEs). Modelling such dynamical systems using Neural Networks i…