Requests for technical support from the VASP group should be posted in the VASP-forum.

Difference between revisions of "ML CTIFOR"

From Vaspwiki
Jump to navigationJump to search
(7 intermediate revisions by 2 users not shown)
Line 4: Line 4:
 
----
 
----
  
During learning, if a newly considered structure yields  a Bayesian  error in the force larger than {{TAG|ML_FF_CTIFOR}}, a first principles calculation is performed, and the corresponding structure is added to the date set of structures that are used when the force field is updated. This flag is only used if {{TAG|ML_FF_IERR}}=2 or 3. The unit of {{TAG|ML_FF_CTIFOR}} is eV/Angstrom. For more details see {{TAG| ML_FF_ISAMPLE }}.
+
During learning, if a newly considered structure yields  a Bayesian  error in the force larger than {{TAG|ML_FF_CTIFOR}}, a first principles calculation is performed, and the corresponding structure is added to the date set of structures that are used when the force field is updated. The unit of {{TAG|ML_FF_CTIFOR}} is eV/Angstrom. If the tag {{TAG|ML_FF_LCRITERIA}}=''.TRUE.'' is set, {{TAG|ML_FF_CTIFOR}} is automatically updated using past Bayesian error estimates for the forces.
  
 
== Related Tags and Sections ==
 
== Related Tags and Sections ==
{{TAG| ML_FF_ISAMPLE }},  {{TAG|ML_FF_LMLFF}}, {{TAG|ML_FF_IERR}}, {{TAG|ML_FF_CSF}}, {{TAG | ML_FF_CDOUB}}
+
{{TAG|ML_FF_LMLFF}}, {{TAG | ML_FF_LCRITERIA}}, {{TAG | ML_FF_CDOUB}}
  
{{sc|ML_FF_C[[Category:VASP6]]
+
{{sc|ML_FF_CTIFOR|Examples|Examples that use this tag}}
TIFOR|Examples|Examples that use this tag}}
 
 
----
 
----
  
[[Category:INCAR]][[Category:Machine Learning]][[Category:Machine Learned Force Fields]][[Category: Alpha]]
+
[[Category:INCAR]][[Category:Machine Learning]][[Category:Machine Learned Force Fields]][[Category:VASP6]][[Category: Alpha]]

Revision as of 10:07, 12 June 2021

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.


During learning, if a newly considered structure yields a Bayesian error in the force larger than ML_FF_CTIFOR, a first principles calculation is performed, and the corresponding structure is added to the date set of structures that are used when the force field is updated. The unit of ML_FF_CTIFOR is eV/Angstrom. If the tag ML_FF_LCRITERIA=.TRUE. is set, ML_FF_CTIFOR is automatically updated using past Bayesian error estimates for the forces.

Related Tags and Sections

ML_FF_LMLFF, ML_FF_LCRITERIA, ML_FF_CDOUB

Examples that use this tag