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

Table 6

The performance of the two timepieces training.

	ResNet-20 on Cafri-10		LSTM on IMDB
	Val-loss	Val-acc	Val-loss	Val-acc
SGD + SGD	0.9409	0.7419	0.6890	0.5831
SGD + RMSprop	0.8670	0.7706	0.4336	0.8367
SGD + Adam	0.8751	0.7641	0.9210	0.8100