| Neural Network Toolbox | |
Normalized dot product weight function
Syntax
Description
normprod is a weight function. Weight functions apply weights to an input to get weighted inputs.
normprod(W,P) takes these inputs,
W - S x R weight matrix.
P - R x Q matrix of Q input (column) vectors.
and returns the S x Q matrix of normalized dot products.
normprod('deriv') returns '' because normprod does not have a derivative function.
Examples
Here we define a random weight matrix W and input vector P and calculate the corresponding weighted input Z.
W = rand(4,3); P = rand(3,1); Z = normprod(W,P)
Network Use
You can create a standard network that uses normprod by calling newgrnn.
To change a network so an input weight uses normprod, set net.inputWeight{i,j}.weightFcn to 'normprod'. For a layer weight, set net.inputWeight{i,j}.weightFcn to 'normprod'.
In either case call sim to simulate the network with normprod. See newgrnn for simulation examples.
Algorithm
normprod returns the dot product normalized by the sum of the input vector elements.
z = w*p/sum(p)
See Also
| | normc | normr | |