Table 3.

Accuracy values (r2) of ensemble DNN compared with other ML models to predict training time

	Best attempt	Dataset size	Meta-leaner (ensemble DNN)	Random forests	Gradient boosted regression trees	Kernel SVM
PB2	5	95	0.84	0.70	0.77	0.70
RW2	3	140	0.83	0.79	0.78	0.79
MB1	3	103	0.81	0.81	0.80	0.70
RR2	4	119	0.79	0.75	0.71	0.69
TR2	2	165	0.87	0.86	0.84	0.83