Neural Network Toolbox

negdist

Negative distance weight function

Syntax

Z = negdist(W,P)

df = negdist('deriv')

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

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

negdist('deriv') returns '' because negdist 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 = 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.inputWeight{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

msereg

netprod

© 1994-2005 The MathWorks, Inc.