Predicting the Number of COVID-19 Sufferers in Malang City Using the Backpropagation Neural Network with the Fletcher–Reeves Method

Table 4

Evaluation results using training data for several architectures with a learning rate of 0.005.

Architecture	MSE		Computational time
	Gradient descent method	Fletcher–Reeves method	Gradient descent method	Fletcher–Reeves method
16-5-1	14471.31	1.31	2.03	0.80
16-20-1	1458.48	1.44	2.13	1.09
16-50-1	394.77	1.27	2.46	2.01
16-100-1	168.11	1.30	4.37	5.09
16-150-1	105.45	1.97	5.37	3.40