ML CTIFOR: Difference between revisions
mNo edit summary |
No edit summary |
||
| Line 3: | Line 3: | ||
Description: This flag sets the threshold for the Bayesian error estimation on the force within the machine learning force field method. | Description: This flag sets the threshold for the Bayesian error estimation on the force within the machine learning force field method. | ||
---- | ---- | ||
The usage of this tag in combination with the learning algorithms is described here: [[Machine learning force field calculations: Important algorithms#Threshold for error of forces|here]]. | |||
During learning, if a newly considered structure yields | During learning, if a newly considered structure yields a Bayesian error in the force larger than {{TAG|ML_CTIFOR}}, a first principles calculation is performed, and the corresponding structure is added to the data set of structures that are used when the force field is updated. The unit of {{TAG|ML_CTIFOR}} is eV/Angstrom. If the tag {{TAG|ML_ICRITERIA}}=''.TRUE.'' is set, {{TAG|ML_CTIFOR}} is automatically updated using past Bayesian error estimates for the forces. | ||
== Related Tags and Sections == | == Related Tags and Sections == | ||
Revision as of 13:37, 21 October 2021
ML_CTIFOR = [real]
Default: ML_CTIFOR =
Description: This flag sets the threshold for the Bayesian error estimation on the force within the machine learning force field method.
The usage of this tag in combination with the learning algorithms is described here: here.
During learning, if a newly considered structure yields a Bayesian error in the force larger than ML_CTIFOR, a first principles calculation is performed, and the corresponding structure is added to the data set of structures that are used when the force field is updated. The unit of ML_CTIFOR is eV/Angstrom. If the tag ML_ICRITERIA=.TRUE. is set, ML_CTIFOR is automatically updated using past Bayesian error estimates for the forces.
Related Tags and Sections
ML_LMLFF, ML_ICRITERIA, ML_CDOUB