Test Set Correlation History vs Iteration

Plot the run's test set correlation history. The correlation coefficient measures how well the network predictions trend with the targets for the cases outside the training set. The correlation range is between -1 to 1. As with the test set RMS error and the test set tolerance history, the correlation history can be used to determine overtraining. While the correlation and RMS errors often trend together, they can give slightly different indications on the onset of overtraining.