XinyuanLiao/Adaptive-optimization-of-PINN

Optimizing Physics-Informed NN using Multi-task Likelihood Loss Balance Algorithm and Adaptive Activation Function Algorithm

29
/ 100
Experimental

This project helps scientific researchers and engineers working with complex physical systems to solve inverse problems more efficiently. It takes in observational data and the governing physical equations, and outputs optimized parameters or conditions of the system. Scientists and engineers who model physical phenomena would use this.

No commits in the last 6 months.

Use this if you need to determine unknown parameters or conditions of a physical system by combining observed data with its underlying physics, especially when dealing with non-linear partial differential equations.

Not ideal if your problem doesn't involve physical equations or requires a more general-purpose machine learning model without physics constraints.

computational-physics inverse-problems scientific-machine-learning physics-informed-AI numerical-modeling
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 7 / 25
Maturity 16 / 25
Community 6 / 25

How are scores calculated?

Stars

33

Forks

2

Language

Python

License

Apache-2.0

Last pushed

Jun 02, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/XinyuanLiao/Adaptive-optimization-of-PINN"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.