Table 4 Hyperparameters for Optimal Model Performance
From: Conceptualisation of Cyberattack prediction with deep learning
Hyperparameter | Experimented Values | Selected Configuration |
|---|---|---|
Number of hidden dense layers | 1 to 10 | 3 |
Neurons per layer | 100 to 1000 | 750, 500, 250 |
Number of epochs | 10 to 500 | 500 |
Batch Size | 32, 64, 128 | 64 |
Learning Rate (lr) | 0.0001, 0.01, 0.1, 0.2, 0.3 | 0.01, 0.1 |