5H3PH3RD

The authors had used Jacobians for predicting the weights ( Fig. attached ) but as you can see from the algo - as we need only the trace of `K`...

Hi everyone! I'm Sagar, a senior undergrad majoring in Mathematics And Computation. Lately, Inverse problem solving through PiNNs has captured my attention (mainly Helmholtz scatterers). I have been working on...

Instead of using the Jacobians for `K` (as implemented) by the authors; I have used dot products because we were only concerned with the main diagonal entries of the `K`...

@xtalax @ChrisRackauckas I have made some changes according to your suggestions. - Two independent commits have been made that deal with the different loss functions - The Inverse Dirichlet is...

Hi Chris, interesting paper. The authors have also released an improved design [PDE-NET 2.0](https://www.sciencedirect.com/science/article/pii/S0021999119306308), where the authors claim to also predict the analytic form of the PDE with good accuracy....