ML MHIS: Difference between revisions
No edit summary |
|||
| Line 14: | Line 14: | ||
---- | ---- | ||
[[Category:INCAR tag]][[Category:Machine | [[Category:INCAR tag]][[Category:Machine-learned force fields]] | ||
Revision as of 13:28, 8 April 2022
ML_MHIS = [integer]
Default: ML_MHIS = 10
Description: This tag sets the number of estimated errors stored in memory to determine the threshold for the Bayesian error in the machine learning force field method.
The usage of this tag in combination with the learning algorithms is described here: here.
This flag is only used if ML_ICRITERIA > 0. The ML code stores ML_MHIS Bayesian errors from previous training steps. Immediately after a training step, the Bayesian error estimate for the forces are reevaluated for the just added training structure, and the maximum error of the forces is stored in the history.
Related tags and articles
ML_LMLFF, ML_ICRITERIA, ML_CTIFOR, ML_CSLOPE, ML_CSIG, ML_CX