Zobrazeno 1 - 10
of 853
pro vyhledávání: '"Koumoutsakos, P."'
Machine learning architectures, including transformers and recurrent neural networks (RNNs) have revolutionized forecasting in applications ranging from text processing to extreme weather. Notably, advanced network architectures, tuned for applicatio
Externí odkaz:
http://arxiv.org/abs/2410.02654
Autor:
Balcerak, Michal, Amiranashvili, Tamaz, Wagner, Andreas, Weidner, Jonas, Karnakov, Petr, Paetzold, Johannes C., Ezhov, Ivan, Koumoutsakos, Petros, Wiestler, Benedikt, Menze, Bjoern
Physical models in the form of partial differential equations serve as important priors for many under-constrained problems. One such application is tumor treatment planning, which relies on accurately estimating the spatial distribution of tumor cel
Externí odkaz:
http://arxiv.org/abs/2409.20409
Autor:
Buhendwa, Aaron B., Bezgin, Deniz A., Karnakov, Petr, Adams, Nikolaus A., Koumoutsakos, Petros
We propose a novel method for inferring the shape of a solid obstacle and its flow field in three-dimensional, steady state supersonic flows. The method combines the optimization of a discrete loss (ODIL) technique with the automatically differentiab
Externí odkaz:
http://arxiv.org/abs/2408.10094
Autor:
Alexeev, Dmitry, Litvinov, Sergey, Economides, Athena, Amoudruz, Lucas, Toner, Mehmet, Koumoutsakos, Petros
The identification of cells and particles based on their transport properties in microfluidic devices is crucial for numerous applications in biology and medicine. Neutrally buoyant particles transported in microfluidic channels, migrate laterally to
Externí odkaz:
http://arxiv.org/abs/2408.09552
We introduce a generative learning framework to model high-dimensional parametric systems using gradient guidance and virtual observations. We consider systems described by Partial Differential Equations (PDEs) discretized with structured or unstruct
Externí odkaz:
http://arxiv.org/abs/2408.00157
Biomedical applications such as targeted drug delivery, microsurgery or sensing rely on reaching precise areas within the body in a minimally invasive way. Artificial bacterial flagella (ABFs) have emerged as potential tools for this task by navigati
Externí odkaz:
http://arxiv.org/abs/2404.02171
We introduce generative models for accelerating simulations of complex systems through learning and evolving their effective dynamics. In the proposed Generative Learning of Effective Dynamics (G-LED), instances of high dimensional data are down samp
Externí odkaz:
http://arxiv.org/abs/2402.17157
Reliable predictions of critical phenomena, such as weather, wildfires and epidemics often rely on models described by Partial Differential Equations (PDEs). However, simulations that capture the full range of spatio-temporal scales described by such
Externí odkaz:
http://arxiv.org/abs/2402.00972
Autor:
Balcerak, Michal, Weidner, Jonas, Karnakov, Petr, Ezhov, Ivan, Litvinov, Sergey, Koumoutsakos, Petros, Zhang, Ray Zirui, Lowengrub, John S., Wiestler, Bene, Menze, Bjoern
Brain tumor growth is unique to each glioma patient and extends beyond what is visible in imaging scans, infiltrating surrounding brain tissue. Understanding these hidden patient-specific progressions is essential for effective therapies. Current tre
Externí odkaz:
http://arxiv.org/abs/2312.05063
Global climate models (GCMs) are the main tools for understanding and predicting climate change. However, due to limited numerical resolutions, these models suffer from major structural uncertainties; e.g., they cannot resolve critical processes such
Externí odkaz:
http://arxiv.org/abs/2312.00907