Neural Network Toolbox

dnetsum

Sum net input derivative function

Syntax

dN_dZ = dnetsum(Z,N)

Description

dnetsum is the net input derivative function for netsum.

dnetsum 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 netsum and then the derivative of N with respect to each weighted input.

• N = netsum(Z1,Z2)
  dN_dZ1 = dnetsum(Z1,N)
  dN_dZ2 = dnetsum(Z2,N)
  

Algorithm

The derivative of a sum with respect to any element of that sum is always a ones matrix that is the same size as the sum.

See Also

netsum, netprod, dnetprod

dnetprod

dotprod

© 1994-2005 The MathWorks, Inc.