no code implementations • 31 May 2024 • Jens Decke, Arne Jenß, Bernhard Sick, Christian Gruhl
This article presents the Sorting Composite Quantile Regression Neural Network (SCQRNN), an advanced quantile regression model designed to prevent quantile crossing and enhance computational efficiency.
no code implementations • 31 May 2024 • Jens Decke, Olaf Wünsch, Bernhard Sick, Christian Gruhl
This article investigates the application of computer vision and graph-based models in solving mesh-based partial differential equations within high-performance computing environments.
1 code implementation • 22 Sep 2023 • Diego Botache, Jens Decke, Winfried Ripken, Abhinay Dornipati, Franz Götz-Hahn, Mohamed Ayeb, Bernhard Sick
This paper presents a methodological framework for training, self-optimising, and self-organising surrogate models to approximate and speed up multiobjective optimisation of technical systems based on multiphysics simulations.
no code implementations • 10 Jul 2023 • Jens Decke, Christian Gruhl, Lukas Rauch, Bernhard Sick
We present two selection strategies for self-optimization to reduce the computational cost in multi-objective design optimization problems.
no code implementations • 9 May 2023 • Jens Decke, Olaf Wünsch, Bernhard Sick
This third representation enables considering the specific data structure of numerical simulations for deep learning approaches.