ML WTIFOR: Difference between revisions

From VASP Wiki
No edit summary
No edit summary
Line 1: Line 1:
{{TAGDEF|ML_WTIFOR|[real]}}
{{TAGDEF|ML_WTIFOR|[real]}}
{{DEF|ML_WTIFOR|0.05|if {{TAG|ML_IWEIGHT}}{{=}}1|1.0|otherwise}}
{{DEF|ML_WTIFOR|0.005|if {{TAG|ML_IWEIGHT}}{{=}}1|1.0|otherwise}}


Description: This tag sets the weight for the scaling of the forces in the training data within the machine learning force field method.
Description: This tag sets the weight for the scaling of the forces in the training data within the machine learning force field method.

Revision as of 13:41, 9 December 2021

ML_WTIFOR = [real] 

Default: ML_WTIFOR = 0.005 if ML_IWEIGHT=1
= 1.0 otherwise

Description: This tag sets the weight for the scaling of the forces in the training data within the machine learning force field method.


ML_IWEIGHT, ML_WTOTEN, ML_WTIFOR, ML_WTSIF form a group of tags which set the normalization and weighting of ab initio training data, i.e. energies, forces and stresses of the training structures. The main control tag is ML_IWEIGHT, please also have a look at its detailed description. If ML_IWEIGHT=1 the weight has unit eV/Angstrom and is used to divide the data by it. For ML_IWEIGHT=2 and 3 the weights are unitless and multiplicative.

Related Tags and Sections

ML_LMLFF, ML_IWEIGHT, ML_WTOTEN, ML_WTSIF, ML_IALGO_LINREG

Examples that use this tag