Neural Network Toolbox™

Plot network performance

Syntax

• plotperf(TR,goal,name,epoch)
  

Description

plotperf(TR,goal,name,epoch) takes these inputs,

TR	Training record returned by train
goal	Performance goal (default = NaN)
name	Training function name (default = '')
epoch	Number of epochs (default = length of training record)

and plots the training performance and, if available, the performance goal, validation performance, and test performance.

Examples

Here are eight input values P and associated targets T, plus a like number of validation inputs VV.P and targets VV.T.

• P = 1:8; T = sin(P);
  VV.P = P; VV.T = T+rand(1,8)*0.1;
  

The code below creates a network and trains it on this problem.

• net = newff(minmax(P),[4 1],{'tansig','tansig'});
  [net,tr] = train(net,P,T,[],[],VV);
  

During training plotperf is called to display the training record. You can also call plotperf directly with the final training record TR, as shown below.

• plotperf(tr)
  

Provide feedback about this page

plotpc

plotperform

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