arXiv subjects

Janine Weber-Hamacher

Publications and source records attributed to Janine Weber-Hamacher.

3 recordsLinked to original sources

arXiv2026

Parallel Training Using a CNN-DNN Architecture for Accelerated Development of Diagnostic Models

Artificial intelligence has shown promise in assisting radiologists in imaging-based diagnosis across a wide range of diseases. Efficient training of large deep learning models is essential to cope with extremely large data sets or dynamically growing disease data, like in a pandemic like situation. In this retrospective study, we collected 300 CT scans from COVID-19 and non-COVID-19 pneumonia patients from three different centers in Germany. We investigated a hybrid CNN-DNN network model based on image decomposition and localization that naturally supports parallel and efficient training of deep learning models. In total, 156 models with three different architectures were trained to capture features at different levels resulting in 12 patient-level COVID-19 diagnosis models. Diagnostic performance as well as time saving were measured. The highest accuracy was obtained from DenseNet121 and 3D CNN models with a parallel CNN-DNN approach, resulting in $88.78\%$ training, $76.67\%$ validation and $76.03\%$ test accuracy for the DenseNet121 with $4\times4\times1$ subdomains and $87.72\%$ training, $76.82\%$ validation and $74.86\%$ test accuracy, respectively, for the 3D CNN with $4\times4\times1$ subdomains. The strongest reduction in parallel training time by a factor of $31$ was observed for the 3D CNN model and $4\times4\times2$ subdomains. Our parallel training approach improves efficiency as well as performance enabling rapid model development, among others crucial for pandemic preparedness.

cs.CV↗

arXiv2026

Mixture of experts surrogate model for the homogenization of open-porous materials

For open-porous materials, incorporating their microstructural properties into mechanical simulations poses a significant challenge for accurately capturing elastic deformation. To deal with this difficulty, multiscale methods are a common tool to couple characteristics of the microstructure of the considered material with the macroscopic material behavior. However, when desiring a high accuracy, these multiscale computations can be computationally very expensive due to the large number of microscopic problems which need to be solved in each compute step. Here, surrogate models that learn the mechanical response of the underlying constitutive model can significantly reduce the computational cost of multiscale approaches. In previous work by some of the authors, beam frame models have been used to model the microstructure of open-porous materials which have been combined with neural network-based surrogate models to approximate the material behavior of a given RVE (repesentative volume element). In this work, we extend our previous study by training a more complex neural network model to predict the mechanical behavior of several RVEs, differing in their maximum pore size and pore-size distribution. Concretely, we focus on mixture of expert (MoE) models and compare different MoE architectures as well as their performance across different RVEs. This novel approach reduces the computational cost of simulating multiple RVEs as the MoE model does not require additional training when new RVEs are considered.

math.NA↗

arXiv2026

Learning Adaptive Coarse Spaces Using Transferable Neural Network Models for Linear and Nonlinear Overlapping Domain Decomposition Methods

Domain decomposition methods have been established as efficient and parallel scalable iterative solvers and preconditioners for the solution of large-scale systems arising from the discretization of partial differential equations. In particular, overlapping Schwarz methods have been successfully applied to a wide range of linear and nonlinear problems. However, for problems with highly heterogeneous coefficients, standard domain decomposition methods typically suffer from deteriorating convergence rates. Robustness with respect to the coefficient contrast can be achieved by enriching the coarse space with adaptively selected constraints obtained from local generalized eigenvalue problems. The construction of these adaptive coarse spaces, however, can account for a significant part of the overall computing time. In the present work, machine learning techniques are employed to reduce this part of the computing time in the context of the adaptive Generalized Dryja-Smith-Widlund (AGDSW) coarse space. A two-stage approach is proposed in which regression neural networks are used to predict the adaptive coarse basis functions, while a classification neural network is employed to predict the number of basis functions required to ensure robustness. As a consequence, adaptive coarse spaces can be set up in the online phase without solving any eigenvalue problem. Particular attention is paid to problem-specific aspects, including sign-invariant loss functions and post-processing strategies to significantly improve the predicted constraints. The proposed approach is first investigated for scalar diffusion problems with high coefficient contrasts and is subsequently transferred, without retraining, to problems of linear elasticity and to nonlinear $p$-Laplace problems, also within a nonlinear Schwarz framework.

math.NA↗