ML CX: Difference between revisions

From VASP Wiki
No edit summary
No edit summary
Line 1: Line 1:
{{TAGDEF|ML_FF_XMIX|[integer]|0.0}}
{{TAGDEF|ML_XMIX|[integer]|0.0}}


Description: The parameter determines how the  threshold  ({{TAG|ML_FF_CTIFOR}}) is updated in the machine learning force field methods.
Description: The parameter determines how the  threshold  ({{TAG|ML_CTIFOR}}) is updated in the machine learning force field methods.
----
----


If {{TAG|ML_FF_ICRITERIA}}>0,  
If {{TAG|ML_ICRITERIA}}>0,  
{{TAG|ML_FF_CTIFOR}} is set to the average of the Bayesian errors of the forces stored in a history (see {{TAG|ML_FF_ICRITERIA}}). The number of entries in the history are controlled by  {{TAG|ML_FF_MHIS}}.
{{TAG|ML_CTIFOR}} is set to the average of the Bayesian errors of the forces stored in a history (see {{TAG|ML_ICRITERIA}}). The number of entries in the history are controlled by  {{TAG|ML_MHIS}}.


{{TAG|ML_FF_CTIFOR}} = (average of the stored Bayesian errors) *(1.0 + {{TAG|ML_FF_XMIX}}).
{{TAG|ML_CTIFOR}} = (average of the stored Bayesian errors) *(1.0 + {{TAG|ML_XMIX}}).


This implies that for {{TAG|ML_FF_XMIX}}=0, the old value stored in {{TAG|ML_FF_CTIFOR}} is simply overwritten by the current average Bayesian error.
This implies that for {{TAG|ML_XMIX}}=0, the old value stored in {{TAG|ML_CTIFOR}} is simply overwritten by the current average Bayesian error.


== Related Tags and Sections ==
== Related Tags and Sections ==
{{TAG|ML_FF_LMLFF}}, {{TAG|ML_FF_ICRITERIA}}, {{TAG|ML_FF_CTIFOR}}, {{TAG|ML_FF_MHIS}}
{{TAG|ML_LMLFF}}, {{TAG|ML_ICRITERIA}}, {{TAG|ML_CTIFOR}}, {{TAG|ML_MHIS}}


{{sc|ML_FF_LCRITERIA|Examples|Examples that use this tag}}
{{sc|ML_LCRITERIA|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: Alpha]]

Revision as of 09:39, 6 September 2021

ML_XMIX = [integer]
Default: ML_XMIX = 0.0 

Description: The parameter determines how the threshold (ML_CTIFOR) is updated in the machine learning force field methods.


If ML_ICRITERIA>0, ML_CTIFOR is set to the average of the Bayesian errors of the forces stored in a history (see ML_ICRITERIA). The number of entries in the history are controlled by ML_MHIS.

ML_CTIFOR = (average of the stored Bayesian errors) *(1.0 + ML_XMIX).

This implies that for ML_XMIX=0, the old value stored in ML_CTIFOR is simply overwritten by the current average Bayesian error.

Related Tags and Sections

ML_LMLFF, ML_ICRITERIA, ML_CTIFOR, ML_MHIS

Examples that use this tag