Table 2.

Performance of the ANNs as a function of the momentum parameter.

		Training Set					Test Set
MP	Score	r²	MAE	RMSE	RAE	RRSE	q²	MAE	RMSE	RAE	RRSE
0.1	0.79	0.78	0.64	0.81	64	68	0.84	0.58	0.73	57	59
0.2	0.80	0.79	0.65	0.82	65	68	0.85	0.6	0.75	59	61
0.3	0.80	0.79	0.66	0.83	66	70	0.85	0.62	0.77	61	63
0.4	0.80	0.79	0.67	0.84	67	71	0.85	0.62	0.78	62	63

Note: MP = momentum parameter; r² = correlation coefficient for the training set; q² = correlation coefficient for the test set (r²_pred); RMSE = root mean square error; MAE = mean absolute error; RAE = relative absolute error; RRSE = root relative squared error; score = (1 − |(r² − q²)|) × q².