msne

Purpose

Mean squared normalized error performance function

Syntax

• perf = msne(E,Y,NET,FP)
  dPerf_dy = msne('dy',E,Y,NET,perf,FP)
  dPerf_dx = msne('dx',E,Y,NET,perf,FP)
  info = msne(code)
  

Description

msne is a network performance function. It measures the network's performance according to the mean of squared normalized errors. Normalized errors are calculated as the difference between targets and outputs after they are each normalized to [-1,1].

The normalization insures that networks with multiple outputs will be trained so that accuracy of each output is treated as equally important. Without normalization outputs with larger values (and therefore larger errors) would be treated as more important.

msne(E,Y,NET,FP) takes these arguments,

E	Matrix or cell array of error vectors
Y	Matrix or cell array of output vectors (ignored)
NET	Neural network
FP	Function parameters (ignored)

and returns the mean squared normalized error.

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

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

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

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

msne('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 neurons.

• net = newff([-10 0 10],[0 0.5 1],4);
  net.performFcn = 'msne';
  

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

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

Network Use

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

In either case, calling train or adapt results in msne's being used to calculate performance.

See Also

mse, msnereg

Provide feedback about this page

mseregec

msnereg

© 1984-2009- The MathWorks, Inc.    -   Site Help   -   Patents   -   Trademarks   -   Privacy Policy   -   Preventing Piracy   -   RSS