Cannot find a connection between any variable and the result of the loss function y=f(x). Please make sure the operations that use variables are inside the function f passed to minimize()

[YoussefSbeiti]

I've been trying to track this error down all day. The losses get computed fine, but tf is not able to compute the gradient because the weights are not used in the loss computation apparently. I checked the code and it looks like the loss function IS using the weights and kernels properly. Any help would be appreciated.