ML CX

From VASP Wiki
Revision as of 09:37, 6 September 2021 by Karsai (talk | contribs)

ML_FF_XMIX = [integer]
Default: ML_FF_XMIX = 1.0 

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


If ML_FF_LCRITERIA is .TRUE., ML_FF_CTIFOR is set to the average of the Bayesian errors of the forces stored in a history (see ML_FF_LCRITERIA). The number of entries in the history are controlled by ML_FF_MHIS.

ML_FF_CTIFOR = (average of the stored Bayesian errors) *(1.0 + ML_FF_XMIX).

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

Related Tags and Sections

ML_FF_LMLFF, ML_FF_LCRITERIA, ML_FF_CTIFOR, ML_FF_MHIS

Examples that use this tag