Results 11 to 20 of about 16,533 (261)
Investigating molecular transport in the human brain from MRI with physics-informed neural networks
Scientific Reports, 2022 In recent years, a plethora of methods combining neural networks and partial differential equations have been developed. A widely known example are physics-informed neural networks, which solve problems involving partial differential equations by ...
Bastian Zapf +5 more
doaj +1 more source
Physics informed neural network consisting of two decoupled stages
Engineering Science and Technology, an International Journal, 2023 This paper proposes a two-stage physics informed neural network (PINN) along with an effective training approach for it. The first stage network output that roughly approximates the solution of a partial differential equation (PDE) is fed as input to the
Nilgun Guler Bayazit
doaj +1 more source
DSFA-PINN: Deep Spectral Feature Aggregation Physics Informed Neural Network
IEEE Access, 2022 Solving parametric partial differential equations using artificial intelligence is taking the pace. It is primarily because conventional numerical solvers are computationally expensive and require significant time to converge a solution. However, physics
Muhammad Rafiq +2 more
doaj +1 more source
Enforcing Dirichlet boundary conditions in physics-informed neural networks and variational physics-informed neural networks [PDF]
Heliyon, 2023 22 pages, 45 ...
Berrone, Stefano +3 more
openaire +7 more sources
Sensors, 2023 A novel type of neural network with an architecture based on physics is proposed. The network structure builds on a body of analytical modifications of classical numerical methods.
Dmitriy Tarkhov +2 more
doaj +1 more source
Physics-Informed Neural Networks for shell structures
European Journal of Mechanics - A/Solids, 2023 ISSN:1873 ...
Jan-Hendrik Bastek, Dennis M. Kochmann
openaire +2 more sources
Physics-Informed Neural Networks for Pathloss Prediction
2023 IEEE 33rd International Workshop on Machine Learning for Signal Processing (MLSP), 2023 This paper introduces a physics-informed machine learning approach for pathloss prediction. This is achieved by including in the training phase simultaneously (i) physical dependencies between spatial loss field and (ii) measured pathloss values in the field.
Steffen Limmer +2 more
openaire +2 more sources
Mathematics, 2023 Physics-Informed Neural Networks (PINNs) improve the efficiency of data utilization by combining physical principles with neural network algorithms and thus ensure that their predictions are consistent and stable with the physical laws.
Zhixiang Liu +4 more
doaj +1 more source
Enhanced physics‐informed neural networks for hyperelasticity
International Journal for Numerical Methods in Engineering, 2022 AbstractPhysics‐informed neural networks have gained growing interest. Specifically, they are used to solve partial differential equations governing several physical phenomena. However, physics‐informed neural network models suffer from several issues and can fail to provide accurate solutions in many scenarios. We discuss a few of these challenges and
Diab W. Abueidda +3 more
openaire +2 more sources