search

idrl-lab / PINNpapers

Must-read Papers on Physics-Informed Neural Networks.
MIT License
787 stars 137 forks source link

Recommending several papers #2

Open smao-astro opened 2 years ago

smao-astro commented 2 years ago

Great job! I wish that I had seen this earlier.

I would like to recommend

  1. When and why PINNs fail to train: A neural tangent kernel perspective
  2. On the eigenvector bias of Fourier feature networks: From regression to solving multi-scale PDEs with physics-informed neural networks
  3. Learning the solution operator of parametric partial differential equations with physics-informed DeepOnets
  4. Long-time integration of parametric evolution equations with physics-informed DeepONets
vaishnavtv commented 2 years ago

Can I also recommend this paper on an Active Learning strategy for generating collocation points in PINNs? Optimal Transport Based Refinement of Physics-Informed Neural Networks