ML CSLOPE: Difference between revisions

From VASP Wiki
No edit summary
No edit summary
 
(7 intermediate revisions by the same user not shown)
Line 1: Line 1:
{{DISPLAYTITLE:ML_CSLOPE}}
{{TAGDEF|ML_CSLOPE|[real]|<math>0.2</math>}}
{{TAGDEF|ML_CSLOPE|[real]|<math>0.2</math>}}


Description: Parameter used in the automatic determination of threshold for Bayesian error estimation in the machine learning force field method.
Description: Parameter used in the automatic determination of threshold for error estimation in the machine learning force field method.
----
----
----For details please read entry {{TAG|ML_ICRITERIA}} first. The parameter {{TAG|ML_CTIFOR}} is only updated, if the absolute of the slope of the collected Bayesian errors is below {{TAG|ML_CSLOPE}} times the mean of the collected Bayesian errors. In practice, the slope and the standard errors are correlated: typically the standard error is at least twice the slope. We recommend to vary only {{TAG|ML_CSIG}} and keep {{TAG|ML_CSLOPE}} fixed to its default value.
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]].
== Related Tags and Sections ==
 
{{TAG|ML_LMLFF}}, {{TAG|ML_ICRITERIA}}, {{TAG|ML_CSIG}}, {{TAG|ML_MHIS}}  
The standard error of the history of maximum estimated errors of the forces ({{TAG|ML_MHIS}}) and it's slope must be below {{TAG|ML_CSIG}} and {{TAG|ML_CSLOPE}} so that an update of the threshold for the maximum estimated error of forces {{TAG|ML_CTIFOR}} can take place.  
 
== Related tags and articles ==
{{TAG|ML_LMLFF}}, {{TAG|ML_ICRITERIA}}, {{TAG|ML_CSIG}}, {{TAG|ML_MHIS}}, {{TAG|ML_CX}}


{{sc|ML_CSLOPE|Examples|Examples that use this tag}}
{{sc|ML_CSLOPE|Examples|Examples that use this tag}}
----
----


[[Category:INCAR]][[Category:Machine Learning]][[Category:Machine Learned Force Fields]][[Category: Alpha]]
[[Category:INCAR tag]][[Category:Machine-learned force fields]]

Latest revision as of 12:29, 12 June 2024

ML_CSLOPE = [real]
Default: ML_CSLOPE =  

Description: Parameter used in the automatic determination of threshold for 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 estimated errors of the forces (ML_MHIS) and it's slope must be below ML_CSIG and ML_CSLOPE so that an update of the threshold for the maximum estimated error of forces ML_CTIFOR can take place.

Related tags and articles

ML_LMLFF, ML_ICRITERIA, ML_CSIG, ML_MHIS, ML_CX

Examples that use this tag