Patrick Zimbrod

icon indicating an email [email protected]

icon company ZEISS Semiconductor Manufacturing Technology icon location Augsburg, Germany icon location Postdoctoral researcher. Excited about numerics for PDEs and physics-informed ML.

Results 2 issues of Patrick Zimbrod

Use `fft` and `rfft` as fit

#31 introduces Fourier Layer for higher dimensions. For now, `rfft` has been replaced by `fft` since it's simpler to implement. However, `rfft` can save memory and computation time considerably (~2x),...

Create a FNO wrapper

In order to assimilate `FourierLayer` to the yet to implement DeepONet, it would be nice to have a Fourier Neural Operator (FNO) constructor that creates the entire architecture. Something like:...

enhancement