NeuralPDE.jl
NeuralPDE.jl copied to clipboard
Physics-Informed Neural Networks (PINN) Solvers of (Partial) Differential Equations for Scientific Machine Learning (SciML) accelerated simulation
There is currently no way to use an array-derived quantity in a NeuralPDE differential equation. This is an example: ``` dx = 0.05 dy = 0.05 xwidth = 10.0 ywidth...
it would be convenient to have one general method for plot of solution. ```julia NeuralPDE.plot(phi, res) ```
Dear "NeuralPDE.jl" Team, can we define the 2D domain as **a plate with a hole**, which may look like: [https://feaforall.com/wp-content/uploads/2013/04/plate-mesh-size.png](url) Thanks in Advance! Libo
`NeuralPDE.KolmogorovPDEProblem`, documented in - https://neuralpde.sciml.ai/dev/solvers/kolmogorovbackwards_solver/ - https://neuralpde.sciml.ai/dev/examples/kolmogorovbackwards/ are `HighDimPDE.PIDEProblem` where the nonlinear term is 0. Associated code and documentation should be migrated to HighDimPDE.jl, which is a more appropriate package...
Currently we use the `ind_vars` of the dependent variable for evaluating the integral. This creates confusion and doesnt allow integrals with `ind_var` as non-integrating variables. Hence we need to structure...
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...
I didn't want that to continue blocking Flux v0.13 (and thus GalacticOptim.jl v3 as well), so I set them as `@test_broken`. I believe it might be just a tolerance thing,...
I just tried to solve a hyperbolic equation with Neumann BCs using adaptive derivative. Unfortunately, it performed badly. The version without the adaptive derivative performed the same. I tried several...
Hey @KirillZubov this is a follow up on the slack question: ``` @Kirill Zubov or anyone, I wanted to write a simple simulation in NeuralPDE with the shallow water equations...