ML CX: Difference between revisions

From VASP Wiki
No edit summary
No edit summary
Line 7: Line 7:
If {{TAG|ML_ICRITERIA}}>0,  
If {{TAG|ML_ICRITERIA}}>0,  
{{TAG|ML_CTIFOR}} is set to the average of the Bayesian errors of the forces stored in history (see {{TAG|ML_ICRITERIA}}). The number of entries in the history are controlled by  {{TAG|ML_MHIS}}.
{{TAG|ML_CTIFOR}} is set to the average of the Bayesian errors of the forces stored in history (see {{TAG|ML_ICRITERIA}}). The number of entries in the history are controlled by  {{TAG|ML_MHIS}}.
{{TAG|ML_CTIFOR}} = (average of the stored Bayesian errors) *(1.0 + {{TAG|ML_CX}}).


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

Revision as of 13:57, 22 October 2021

ML_CX = [integer]
Default: ML_CX = 0.0 

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


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

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

This implies that for ML_CX=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, ML_CSIG, ML_CSLOPE

Examples that use this tag