Table 3

Results for a neural network constructed of 78 neurons, following training for ≤100 epochs (see Eq. (1)). The number of each training vector for both treatment and retreatment groups is 30. Each time, the procedure continues until the mean square error is minimized within the ≤100 number of epochs. Following the training procedure, two groups (c-correct case and r-retreat case) of vectors are constructed (see Eq. (9)). The procedure is repeated eight times with randomly constructed training vectors so that eight equivalent but different neural LVQ networks are constructed. The results of the eight repetitions are then averaged to permit a best estimate of the network’s performance.

Neural networks	Best training performance in number of epochs ≤100	Retreat classification results		Correct classification results
		Total 70		Total 2308
		True	False	True	False
Net 1		0.7466	0.2534	0.7154	0.2846
Net 2		0.7177	0.2823	0.6538	0.3462
Net 3		0.6594	0.3406	0.6923	0.3077
Net 4		0.6937	0.3063	0.7385	0.2615
Net 5		0.6542	0.3458	0.7000	0.3000
Net 6		0.6570	0.3430	0.7000	0.3000
Net 7		0.6455	0.3545	0.7231	0.2769
Net 8		0.6995	0.3005	0.6915	0.3085
Mean (Net)		0.6842	0.3158	0.7018	0.2982