Table 1.
Hyperparameter | param-1 | param-2 | param-3 | param-4 | param-5 | param-6 |
---|---|---|---|---|---|---|
learning-rate | 0.1 | 0.01 | 0.001 | – | – | – |
layers & nodes | [32, 32] | [32, 64] | [32, 64, 128] | [32, 64, 128, 256] | [32, 64, 128, 256, 512] | – |
dropout | 0.0 | 0.1 | 0.2 | 0.3 | 0.4 | 0.5 |
The bold values represent the tuned hyperparameters resulted from the grid search approach.
The symbol “–” means that the corresponding value or field is empty or has no data.