ML MB: Difference between revisions

From VASP Wiki
No edit summary
No edit summary
Line 1: Line 1:
{{TAGDEF|ML_FF_MB_MB|[integer]|1000}}
{{TAGDEF|ML_FF_MB_MB|[integer]|1000}}


Description: This flag sets the maximum number of basis sets describing the many-body interactions in the machine learning force field method.
Description: This flag sets the maximum number of local configurations (basis sets) describing the many-body interactions in the machine learning force field method.
----
----
The default value is usually a safe value but should be set to a higher value as soon as it is reached. In this case the previous learning calculation should be repeated. By using {{TAG|ML_FF_LBASIS_DISCARD}}=''.FALSE.'' (default setting for this tag) it can be easily detected if {{TAG|ML_FF_MB_MB}} is reached, since the learning would simply stop.
The default value is usually a safe value but should be set to a higher value as soon as it is reached. In this case the previous learning calculation should be repeated. By using {{TAG|ML_FF_LBASIS_DISCARD}}=''.FALSE.'' (default setting for this tag) it can be easily detected if {{TAG|ML_FF_MB_MB}} is reached, since the learning would simply stop.

Revision as of 08:36, 13 December 2019

ML_FF_MB_MB = [integer]
Default: ML_FF_MB_MB = 1000 

Description: This flag sets the maximum number of local configurations (basis sets) describing the many-body interactions in the machine learning force field method.


The default value is usually a safe value but should be set to a higher value as soon as it is reached. In this case the previous learning calculation should be repeated. By using ML_FF_LBASIS_DISCARD=.FALSE. (default setting for this tag) it can be easily detected if ML_FF_MB_MB is reached, since the learning would simply stop.

Related Tags and Sections

ML_FF_LMLFF, ML_FF_LBASIS_DISCARD, ML_FF_MCONF, ML_FF_LCONF_DISCARD

Examples that use this tag