ML CTIFOR: Difference between revisions
No edit summary |
No edit summary |
||
| Line 9: | Line 9: | ||
{{TAG|ML_FF_LMLFF}}, {{TAG|ML_FF_IERR}}, {{TAG|ML_FF_CSF}} | {{TAG|ML_FF_LMLFF}}, {{TAG|ML_FF_IERR}}, {{TAG|ML_FF_CSF}} | ||
{{sc| | {{sc|ML_FF_C[[Category:VASP6]] | ||
TIFOR|Examples|Examples that use this tag}} | |||
---- | ---- | ||
[[Category:INCAR]][[Category:Machine Learning]][[Category:Machine Learned Force Fields | [[Category:INCAR]][[Category:Machine Learning]][[Category:Machine Learned Force Fields]] | ||
Revision as of 10:49, 30 January 2020
ML_FF_CTIFOR = [real]
Default: ML_FF_CTIFOR =
Description: This flag sets the threshold for the Bayesian error estimation on the force in the machine learning force field method.
Within the learning step if a newly considered structure gives an error in the force larger than ML_FF_CTIFOR, the sampling is stopped and a new force field is generated. This flag is only used if ML_FF_IERR=2 or 3. The unit of ML_FF_CTIFOR is eV/Angstrom.
Related Tags and Sections
ML_FF_LMLFF, ML_FF_IERR, ML_FF_CSF
[[Special:Search/"ML_FF_C TIFOR" incategory:"Examples"|Examples that use this tag]]