Deep Learning Approaches for Predictive Masquerade Detection

Table 5

The used DNN hyperparameters and their domains.

Hyperparameter	Domain	Description
Learning rate		Continuous
Momentum		Continuous
Decay		Continuous
Dropout rate		Continuous
Number of hidden layers		Discrete with step=1
Numbers of neurons of hidden layers		Discrete with step=1
Number of epochs		Discrete with step=5
Batch size		Discrete with step=50
Optimizer		Discrete with step=1
Initialization function		Discrete with step=1
Layer type		Discrete with step=1
Activation function		Discrete with step=1