[Retracted] Gradient Descent Optimization in Deep Learning Model Training Based on Multistage and Method Combination Strategy

Table 7

The performance of the three timepieces training.

	ResNet-20 on Cafri-10		LSTM on IMDB
	Val-loss	Val-acc	Val-loss	Val-acc
SGD + SGD + SGD	0.8673	0.7599	0.6341	0.6461
SGD + RMSprop + SGD	0.5108	0.8822	0.4824	0.8330
SGD + Adam + SGD	0.5994	0.8524	0.9417	0.8112