ML CTIFOR: Difference between revisions

From VASP Wiki
No edit summary
No edit summary
Line 4: Line 4:
----
----
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]].
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 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.

Related Tags and Sections

ML_LMLFF, ML_ICRITERIA, ML_CDOUB

Examples that use this tag