TABLE I.
Hyperparameter search space
| Hyperparameter | Values |
|---|---|
| Batch Size | 10–1000 |
| Number of Hidden Layers | 1–7 |
| Layer Width | 520–1040 |
| Input Gaussian Noise | True or False |
| Input Dropout Probability | 0–0.5 |
| Hidden Node Dropout Probability | 0–0.5 |
| Batch Norm | True or False |
| Loss Function | L1, L2, Smooth L1 |
| Weight Decay | 0, 0.0001, 0.001 |