-
Notifications
You must be signed in to change notification settings - Fork 5
Experiments
Marcus Wieder edited this page May 25, 2024
·
13 revisions
Training for each neural network is performed on a fixed testset with each implemented neural network potential. We repeat each training 5 times with random parameter initialization.
| NNP | average number of epochs | time @ epoch [min:sec] | RMSE test set [kcal/mol] | reported performance [kcal/mol |
|---|---|---|---|---|
| ANI2x | 282 | 0:10 | 0.5 | |
| SchNet | 500 | 0:55 | 0.9 +- | MAE: 0.322848 |
| PaiNN | 300 | 1:10 | 0.6 | |
| PhysNet | 1:00 | |||
| SAKE | ||||
| TensorNet | ||||
| MACE | ||||
| SpookyNet |