This example shows how to use plotperform to obtain a plot of training record error values against the number of training epochs.

[x,t] = bodyfat_dataset;
net = feedforwardnet(10);
[net,tr] = train(net,x,t);
plotperform(tr)

Generally, the error reduces after more epochs of training, but might start to increase on the validation data set as the network starts overfitting the training data. In the default setup, the training stops after six consecutive increases in validation error, and the best performance is taken from the epoch with the lowest validation error.