dnetprod (Neural Network Toolbox)

Derivative of net input product function

dN_dZ = dnetprod(Z,N)

dnetprod is the net input derivative function for netprod.

dnetprod takes two arguments,

Z - S x Q weighted input.

N - S x Q net input.

and returns the S x Q derivative dN/dZ.

Examples

Here we define two weighted inputs for a layer with three neurons.

Z1 = [0; 1; -1];
Z2 = [1; 0.5; 1.2];

We calculate the layer's net input N with netprod and then the derivative of N with respect to each weighted input.

N = netprod(Z1,Z2)
dN_dZ1 = dnetprod(Z1,N)
dN_dZ2 = dnetprod(Z2,N)

The derivative a product with respect to any element of that product is the product of the other elements.