Neural Network Toolbox™

Convolution weight function

Syntax

• Z = convwf(W,P)
  dim = convwf('size',S,R,FP)
  dp = convwf('dp',W,P,Z,FP)
  dw = convwf('dw',W,P,Z,FP)
  info = convwf(code)
  

Description

convwf is the convolution weight function. Weight functions apply weights to an input to get weighted inputs.

convwf(code) returns information about this function. The following codes are defined:

'deriv'	Name of derivative function
'fullderiv'	Reduced derivative = 2, full derivative = 1, linear derivative = 0
'pfullderiv'	Input: reduced derivative = 2, full derivative = 1, linear derivative = 0
'wfullderiv'	Weight: reduced derivative = 2, full derivative = 1, linear derivative = 0
'name'	Full name
'fpnames'	Returns names of function parameters
'fpdefaults'	Returns default function parameters

convwf('size',S,R,FP) takes the layer dimension S, input dimension R, and function parameters, and returns the weight size.

convwf('dp',W,P,Z,FP) returns the derivative of Z with respect to P.

convwf('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(4,1);
  P = rand(8,1);
  Z = convwf(W,P)
  

Network Use

To change a network so an input weight uses convwf, set net.inputWeight{i,j}.weightFcn to 'convwf'. For a layer weight, set net.layerWeight{i,j}.weightFcn to 'convwf'.

In either case, call sim to simulate the network with convwf.

Provide feedback about this page

confusion

disp

© 1984-2008- The MathWorks, Inc.    -   Site Help   -   Patents   -   Trademarks   -   Privacy Policy   -   Preventing Piracy   -   RSS