normprod

(To be removed) Normalized dot product weight function

normprod will be removed in a future release. For more information, see Transition Legacy Neural Network Code to dlnetwork Workflows.

For advice on updating your code, see Version History.

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.

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

R2026a: normprod will be removed

normprod will be removed in a future release.

To learn more about supported mathematical and deep learning operations and layers, see these examples and topics:

• Build Networks with Deep Network Designer

• List of Deep Learning Layers

• List of Functions with dlarray Support

For more information, see Transition Legacy Neural Network Code to dlnetwork Workflows.