Table 4.
Comparison of the performances of models with different numbers of self-attention layers.
| Number of self-attention layers | MAE | RMSE | PCC |
|---|---|---|---|
| 1 | 7.07 ± 0.61 | 9.49 ± 0.72 | 0.30 ± 0.14 |
| 2 | 5.92 ±0.62 | 7.56 ±0.78 | 0.44 ±0.11 |
| 3 | 6.70 ± 0.79 | 8.48 ± 0.93 | 0.34 ± 0.12 |
| 4 | 6.95 ± 0.52 | 8.97 ± 0.79 | 0.28 ± 0.14 |