ML MCONF NEW
ML_MCONF_NEW = [integer]
Default: ML_MCONF_NEW = 5
Description: This tag sets the number of configurations that are stored temporarily as candidates for the training data in the machine learning force field method.
| Warning: This value is empirically set and should usually not be touched. |
Usually one can employ that the force field doesn't necessary needs to be retrained immediately at every step when a training structure with corresponding local configurations is added. Instead one can also collect candidates and do the learning in a later step for all structures simultaneously. This way saving significant computational cost is saved. Of course learning after every new configurations or after every blocks can have different results, but with not too large block size the difference should be small.
The tag ML_MCONF_NEW sets the block size for learning. If the Bayesian error of the force for any atom is above the threshold ML_CTIFOR but below ML_CDOUBML_CTIFOR, the structure is added to the list of new training structures. Whenever the number of candidates is equal to ML_MCONF_NEW the new training structures are added to the training structures and the force field is updated. To avoid sampling of too similar structures the next step from which on training structures are allowed to be taken as candidates is set by ML_NMDINT. All ab initio calculations within this distance are skipped if the Bayesian error for the force on all atoms is below ML_CDOUBML_CTIFOR. If the error at any time is above ML_CDOUBML_CTIFOR immediately the candidates are added to the list of training structure and the force field is updated. This is like an emergency break which won't allow the force field to drift too far away from the ab initio trajectories.