normprod

Normalized dot product weight function

Syntax

Z = normprod(W,P,FP) dim = normprod('size',S,R,FP) dw = normprod('dz_dw',W,P,Z,FP)

Description

normprod is a weight function. Weight functions apply weights to an input to get weighted inputs.

Z = normprod(W,P,FP) takes these inputs,

`W`	`S`-by-`R` weight matrix
`P`	`R`-by-`Q` matrix of `Q` input (column) vectors
`FP`	Row cell array of function parameters (optional, ignored)

and returns the S-by-Q matrix of normalized dot products.

dim = normprod('size',S,R,FP) takes the layer dimension S, input dimension R, and function parameters, and returns the weight size [S-by-R].

dw = normprod('dz_dw',W,P,Z,FP) returns the derivative of Z with respect to W.

Examples

Here you 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.inputWeights{i,j}.weightFcn to 'normprod'. For a layer weight, set net.layerWeights{i,j}.weightFcn to 'normprod'.

In either case, call sim to simulate the network with normprod. See newgrnn for simulation examples.

Algorithms

normprod returns the dot product normalized by the sum of the input vector elements.

z = w*p/sum(p)

Version History

Introduced before R2006a