Neural Network Toolbox™

Sum squared error performance function

Syntax

• perf = sse(E,Y,X,FP)
  dPerf_dy = sse('dy',E,Y,X,perf,FP);
  dPerf_dx = sse('dx',E,Y,X,perf,FP);
  info = sse(code)
  

Description

sse is a network performance function. It measures performance according to the sum of squared errors.

sse(E,Y,X,FP) takes E and optional function parameters,

E	Matrix or cell array of error vectors
Y	Matrix or cell array of output vectors (ignored)
X	Vector of all weight and bias values (ignored)
FP	Function parameters (ignored)

and returns the sum squared error.

sse('dy',E,Y,X,perf,FP) returns the derivative of perf with respect to Y.

sse('dx',E,Y,X,perf,FP) returns the derivative of perf with respect to X.

sse('name') returns the name of this function.

sse('pnames') returns the names of the training parameters.

sse('pdefaults') returns the default function parameters.

Examples

Here a two-layer feed-forward network is created with a one-element input ranging from -10 to 10, four hidden tansig neurons, and one purelin output neuron.

• net = newff([-10 10],[4 1],{'tansig','purelin'});
  

The network is given a batch of inputs P. The error is calculated by subtracting the output A from target T. Then the sum squared error is calculated.

• p = [-10 -5 0 5 10];
  t = [0 0 1 1 1];
  y = sim(net,p)
  e = t-y
  perf = sse(e)
  

Note that sse can be called with only one argument because the other arguments are ignored. sse supports those arguments to conform to the standard performance function argument list.

Network Use

To prepare a custom network to be trained with sse, set net.performFcn to 'sse'. This automatically sets net.performParam to the empty matrix [], because sse has no performance parameters.

Calling train or adapt results in sse's being used to calculate performance.

Provide feedback about this page

srchhyb

tansig

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