Parallel and scalable AI in HPC systems for CFD applications and beyond

Autor: Rakesh Sarma, Eray Inanc, Marcel Aach, Andreas Lintermann

Publikováno v: Frontiers in High Performance Computing, Vol 2 (2024)

This manuscript presents the library AI4HPC with its architecture and components. The library enables large-scale trainings of AI models on High-Performance Computing systems. It addresses challenges in handling non-uniform datasets through data mani

Externí odkaz: https://doaj.org/article/1de2ecdf8f244483a492e7adc9d72a3a

Turbulent Flow Prediction-Simulation: Strained Flow with Initial Isotropic Condition Using a GRU Model Trained by an Experimental Lagrangian Framework, with Emphasis on Hyperparameter Optimization

Autor: Reza Hassanian, Marcel Aach, Andreas Lintermann, Ásdís Helgadóttir, Morris Riedel

Publikováno v: Fluids, Vol 9, Iss 4, p 84 (2024)

This study presents a novel approach to using a gated recurrent unit (GRU) model, a deep neural network, to predict turbulent flows in a Lagrangian framework. The emerging velocity field is predicted based on experimental data from a strained turbule

Externí odkaz: https://doaj.org/article/6eadbcce9cbd4b0a853fb639370a94b0

Accelerating Hyperparameter Tuning of a Deep Learning Model for Remote Sensing Image Classification

Autor: Marcel Aach, Rocco Sedona, Andreas Lintermann, Gabriele Cavallaro, Helmut Neukirchen, Morris Riedel

Publikováno v: IEEE 263-266 (2022). doi:10.1109/IGARSS46834.2022.9883257
2022 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2022, Kuala Lumpur, Malaysia, 2022-07-17-2022-07-22

Deep Learning models have proven necessary in dealing with the challenges posed by the continuous growth of data volume acquired from satellites and the increasing complexity of new Remote Sensing applications. To obtain the best performance from suc

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::68a60c094f12b5f587ce2e36ef03550a
https://hdl.handle.net/2128/32035

Speed-Up of Machine Learning for Sound Localization via High-Performance Computing

Autor: Eric Michael Sumner, Marcel Aach, Andreas Lintermann, Runar Unnthorsson, Morris Riedel

Publikováno v: 2022 26th International Conference on Information Technology (IT)
IEEE 1-4 (2022). doi:10.1109/IT54280.2022.9743519
26th International Conference on Information Technology (IT), IT, Zabljak, Montenegro, 2022-02-16-2022-02-19

Post-print (lokaútgáfa höfunda).
Sound localization is the ability of humans to determine the source direction of sounds that they hear. Emulating this capability in virtual environments can have various societally relevant applications enabl

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::bc9cf7bed448bb8aa0b5a2337182162c

Large scale performance analysis of distributed deep learning frameworks for convolutional neural networks.

Autor: Aach, Marcel, Inanc, Eray, Sarma, Rakesh, Riedel, Morris, Lintermann, Andreas

Publikováno v: Journal of Big Data; 6/8/2023, Vol. 10 Issue 1, p1-23, 23p