ML CSIG: Difference between revisions

From VASP Wiki
No edit summary
No edit summary
Line 5: Line 5:
----
----
The usage of this tag in combination with the learning algorithms is described here: [[Machine learning force field calculations: Basics#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: Basics#Threshold for error of forces|here]].
The standard error of the history of maximum Bayesian errors of the forces ({{TAG|ML_HIS}}) and it's slope must be below {{TAG|ML_CSIG}} and {{TAG|CSLOPE}} so that an update of the threshold for the maximum Bayesian error of forces {{TAG|ML_CTIFOR}} can take place.


== Related Tags and Sections ==
== Related Tags and Sections ==

Revision as of 10:20, 2 November 2021

ML_CSIG = [real]
Default: ML_CSIG =  

Description: Parameter used in the automatic determination of threshold ML_CTIFOR for Bayesian error estimation in the machine learning force field method.


The usage of this tag in combination with the learning algorithms is described here: here.

The standard error of the history of maximum Bayesian errors of the forces (ML_HIS) and it's slope must be below ML_CSIG and CSLOPE so that an update of the threshold for the maximum Bayesian error of forces ML_CTIFOR can take place.

Related Tags and Sections

ML_LMLFF, ML_ICRITERIA, ML_CSLOPE, ML_MHIS, ML_CTIFOR, ML_CX

Examples that use this tag