Table 4 Hyperparameters search space of the risk assessment network

Batch size

[8, 16]

# hidden layers for both SN (\({L_S}\)) and CSNs (\({L_C}\))

[1, 2, 3, 5]

# neurons per hidden layer

[20, 50, 100, 200]

Dropout rate

[0.2, 0.3, 0.4]

Activation function

[ReLU, SELU]

\(\alpha \)

[0.1, 0.5, 1.0, 3.0]

Loss function \(\mathcal{L}\)\(\beta \)

[0.1, 0.5, 1.0, 3.0]

\(\gamma \)

[0.1, 0.5, 1.0, 3.0]