Hi All,
Is it possible to calculate the gradients of an intermediate variable with respect to an input?
The layout is as follows:
intermediate = g(inp1)
output = f(inp1, intermediate,…)
To do so, we minimize the loss: Solve MSE optimization problem loss ||output-target||
Then after the model is trained I am interested in finding the sensitivities of an intermediate variable:
d(intermediate)/d(inp1),