Solving for part of a PDE system.

[knuds]

If you have 2 or more functions as Neural nets, say f and g.
And they are coupled by a differential equation.
If we already idea how f should look like say we have a mock function f_m for f
I would like to:

1. Train f to f_m.
2. Solve/optimize the PDE for g, without updating f.
3. Then solve/optimize the PDE for f, without updating g.

We need at way to tell the optimizer to not optimize on some functions.