Table 1.
All hyperparameters and their values that are optimized for the different machine learning models
| hyper-parameter | MLP | RNN | CNN |
|---|---|---|---|
| batch size | 16, 32, 64 | 16, 32, 64 | 16, 32, 64 |
| Dropout | 0.2, 0.4 | 0.2, 0.4 | 0.2, 0.4 |
| kernel regularizer | 10−4, 10−3, 10−2 | 10−4, 10−3, 10−2 | 10−4, 10−3, 10−2 |
| activation dense | ELU, ReLU | ELU, ReLU | ELU, ReLU |
| number of layers | 2, 4, 8 | 2, 4, 8 | 2, 4, 8 |
| learning rate | 10−4, 10−3, 10−2 | 10−4, 10−3, 10−2 | 10−4, 10−3, 10−2 |
| no. of units/filters | 256, 512, 1024 | 32, 64 | 64, 128, 256 |
| cell type | – | – | GRU, LSTM |
| recurrent dropout | – | – | 0, 0.2, 0.4 |
| bidirectional | – | – | true, false |