Modeling the Spread of COVID-19 Infection Using a Multilayer Perceptron

Table 1

Hyperparameters used in training. First column lists the hyperparameter name, while the possible values of the hyperparameter are listed in the second column. The last column presents the number of hyperparameters, with the last row showing the total number of hyperparameter combinations, obtained and used during the grid search algorithm execution.

Hyperparameter	Possible values	Count
Solver	Adam, LBFGS	2
Initial learning rate	0.00001, 0.01, 0.1, 0.5	4
Learning rate adjustment	Constant, adaptive, invscaling	3
Hidden layer sizes	(3), (6), (4, 4), (3, 3, 3), (6, 6, 6), (4, 3, 4), (12, 12, 12), (4, 4, 3, 3), (4, 4, 4, 4), (6, 6, 6, 6), (10, 5, 5, 10), (3, 3, 3, 3, 3), (10, 10, 10, 10, 10), (12, 12, 6, 6, 3, 3)	14
Activation functions	ReLU, identity, logistic, tanh	4
Regularization parameter	0.00001, 0.001, 0.01, 0.1	4
Total number of hyperparameter combinations		5376