Gradient descent algorithms take the loss function and use partial derivatives to determine what each variable (weights and biases) in the network contributed to the loss value.

We generalize the notions of the fractional g-integral and g-derivative by introducing variable lower limit of integration. We discuss some properties and their relations. Finally, we give a ...

Zhimin Zhang, Derivative Superconvergent Points in Finite Element Solutions of Harmonic Functions: A Theoretical Justification, Mathematics of Computation, Vol. 71, No. 240 (Oct., 2002), pp. 1421-1430 ...