29 citations · 38 across the 4 of their papers we have counts for
4 papers
Approximate Equivariance via Projection-based Regularisation
Torben Berndt, Jan Stühmer
Equivariance is a powerful inductive bias in neural networks, improving generalisation and physical consistency. Recently, however, non-equivariant models have regained attention,…
Graph Neural Networks and Spatial Information Learning for Post-Processing Ensemble Weather Forecasts
Moritz Feik, Sebastian Lerch, Jan Stühmer
Ensemble forecasts from numerical weather prediction models show systematic errors that require correction via post-processing. While there has been substantial progress in flexibl…
Grappa -- A Machine Learned Molecular Mechanics Force Field
Leif Seute, Eric Hartmann, Jan Stühmer +1
Simulating large molecular systems over long timescales requires force fields that are both accurate and efficient. In recent years, E(3) equivariant neural networks have lifted th…
Independent Subspace Analysis for Unsupervised Learning of Disentangled Representations
Jan Stühmer, Richard E. Turner, Sebastian Nowozin
Recently there has been an increased interest in unsupervised learning of disentangled representations using the Variational Autoencoder (VAE) framework. Most of the existing work…