Neural Network Toolbox™

Negative distance weight function

Syntax

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

Description

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

negdist(W,P) takes these inputs,

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

and returns the S x Q matrix of negative vector distances.

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

'deriv'	Name of derivative function
'fullderiv'	Full derivative = 1, linear derivative = 0
'name'	Full name
'fpnames'	Returns names of function parameters
'fpdefaults'	Returns default function parameters

negdist('size',S,R,FP) takes the layer dimension S, input dimension R, and function parameters, and returns the weight size [S x R].

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

negdist('size',S,R,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 = negdist(W,P)
  

Network Use

You can create a standard network that uses negdist by calling newc or newsom.

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

In either case, call sim to simulate the network with negdist. See newc or newsom for simulation examples.

Algorithm

negdist returns the negative Euclidean distance:

• z = -sqrt(sum(w-p)^2)
  

See Also

sim, dotprod, dist

Provide feedback about this page

nctool

netinv

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