Time-dependent partial differential equations (PDEs) are ubiquitous in
s...
We contribute to the vastly growing field of machine learning for engine...
We introduce Clifford Group Equivariant Neural Networks: a novel approac...
We contribute to the vastly growing field of machine learning for engine...
Graph neural networks (GNNs) have evolved into one of the most popular d...
We propose Geometric Clifford Algebra Networks (GCANs) that are based on...
Most state-of-the-art approaches for weather and climate modeling are ba...
Partial differential equations (PDEs) are central to describing complex
...
Partial differential equations (PDEs) see widespread use in sciences and...
We introduce SubGD, a novel few-shot learning method which is based on t...
Neural networks are increasingly being used to solve partial differentia...
The numerical solution of partial differential equations (PDEs) is diffi...
Including covariant information, such as position, force, velocity or sp...
The abundance of data has given machine learning huge momentum in natura...
Recently, the application of machine learning models has gained momentum...
We prove under commonly used assumptions the convergence of actor-critic...
In order to quickly adapt to new data, few-shot learning aims at learnin...
Reinforcement Learning algorithms require a large number of samples to s...
We show that the transformer attention mechanism is the update rule of a...
Climate change affects occurrences of floods and droughts worldwide. How...
We demonstrate how machine learning is able to model experiments in quan...