Zoe McCarthy
Zoe McCarthy
Very WIP, I'm pulling in and merging prototypes of the various components into the main repo. This depends on the adaptive reweighting stuff and so that should be finalized and...
@hpieper14 @ChrisRackauckas @frankschae @KirillZubov Design discussions here so that they don't get slurped up by slack.
I'm working on a systematic expansion and review of the tests for PINNs: - [ ] Many PINN tests compare to the analytic solution but only using a test like:...
Currently you have to do a bit of parameter counting & slicing wizardry to even evaluate each of the pde functions' FastChains given the whole parameter vector and the vector...
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...
Implementing the Magnitude Normalization adaptive loss method proposed in this paper "Optimally weighted loss functions for solving PDEs with Neural Networks" [paper](https://arxiv.org/abs/2002.06269) by Remco van der Meer, Cornelis Oosterlee, Anastasia...
Implement the Multiscale Fourier Features (MFF) neural network architecture proposed in this paper "On the eigenvector bias of Fourier feature networks: From regression to solving multi-scale PDEs with physics-informed neural...