Dear Colleagues/Researchers,
Can you recommend any papers/research on using PINNs (Physics Informed Neural Networks) to solve direct (and potentially) inverse eigenvalue/spectral problems?
One related work is this: https://www.sciencedirect.com/science/article/abs/pii/S1007570421003531
Any further suggestions or projects (potentially including code)?
Thanks.
There are several papers on using physics-informed neural networks (PINNs) to solve eigenvalue/spectral problems. Some examples include:
Dear Rudra Tiwari,
Thanks a lot for your reply. Could you please provide the corresponding DOI of your recommendations? I couldn't locate these articles.
For example, the first reference you say "A physics-informed neural network approach for solving the eigenvalue problem" by Raissi et al. (2019), is probably this: Article Physics-Informed Neural Networks: A Deep Learning Framework ...
which doesn't consider any eigenvalue problems.
Best regards.
After some searching, I came to the following papers related with NN and eigenvalue problems:
1. "Physics-Informed Neural Networks for Quantum Eigenvalue Problems", by Henry Jin, Marios Mattheakis and Pavlos Protopapas, 2022
https://ieeexplore.ieee.org/document/9891944
2. "Neural Networks Base on Power Method and Inverse Power Method for Solving Linear Eigenvalue Problems" by Qihong Yanga , Yangtao Denga , Yu Yanga , Qiaolin Hea and Shiquan Zhanga, 2022
https://arxiv.org/pdf/2209.11134.pdf
Any further contribution is very welcome!
- Badges
- Science topic
- Similar topics
- Engineering
- Modeling