NeuralPDE.jl
NeuralPDE.jl copied to clipboard
Physics-Informed Neural Networks (PINN) Solvers of (Partial) Differential Equations for Scientific Machine Learning (SciML) accelerated simulation
From the conversation here https://github.com/SciML/NeuralPDE.jl/issues/390#issuecomment-921892269 We should ammortize the integral cost. I.e., if we integrate from (0,x), then the next point is at (0,y), we really only need to solve...
https://arxiv.org/pdf/2104.10013.pdf - [ ] GPU - [ ] multi-GPU - [ ] MPI
I had a generally positive experience working with higher dimensional PDEs, but I struggled to figure out how to analyze the results of these 3D+ PDEs effectively. I think it...
https://proceedings.neurips.cc/paper/2021/file/df438e5206f31600e6ae4af72f2725f1-Paper.pdf
It's never a good idea, so it's bad form. We shouldn't show people bad form and then tell them to not do it in issues.
Implementing the Neural Tangent Kernel adaptive loss method proposed in the "When and Why PINNs Fail to Train: A Neural Tangent Kernel Perspective" [paper](https://arxiv.org/pdf/2007.14527.pdf) by Sifan Wang, Xinling Yu, Paris...
Implementing the Inverse Dirichlet adaptive loss method proposed in this paper "Inverse Dirichlet weighting enables reliable training of physics informed neural networks" [paper](https://iopscience.iop.org/article/10.1088/2632-2153/ac3712/pdf) by Suryanarayana Maddu, Dominik Sturm, Christian L...