One time you evaluated the derivate at 1.0 instead of 2.0, why did you get the same result?
@kefre10 Жыл бұрын
Ah it needs the cotangend at this point
@MachineLearningSimulation Жыл бұрын
Great question! 😊 Yes, you figured it out. The pullback at lines 57 and 61 give the derivative if evaluated at 1.0. Since they effectively evaluate the vector-Jacobian product we need to provide a vector (here just a scalar) to left-multiply the Jacobian with. Using just 1.0 gives the unscaled derivative.