ML CDOUB: Difference between revisions
m (Karsai moved page ML FF CDOUB to ML CDOUB) |
No edit summary |
||
| Line 1: | Line 1: | ||
{{TAGDEF| | {{TAGDEF|ML_CDOUB|[real]|2.0}} | ||
Description: This flag controls the necessity of DFT calculations in the machine learning force field method. | Description: This flag controls the necessity of DFT calculations in the machine learning force field method. | ||
---- | ---- | ||
If at any time, the estimated errors are {{TAG| | If at any time, the estimated errors are {{TAG|ML_CDOUB}} times larger than the Bayesian threshold, a first principles calculation is performed and a new force field is immediately generated (even if the counter for sampling is below the minimum amount of sampled structures {{TAG|ML_NMDINT}}). | ||
== Related Tags and Sections == | == Related Tags and Sections == | ||
{{TAG| | {{TAG|ML_LMLFF}}, {{TAG|ML_CTIFOR}}, {{TAG|ML_NMDINT}} | ||
{{sc| | {{sc|ML_CDOUB|Examples|Examples that use this tag}} | ||
---- | ---- | ||
[[Category:INCAR]][[Category:Machine Learning]][[Category:Machine Learned Force Fields]][[Category: Alpha]] | [[Category:INCAR]][[Category:Machine Learning]][[Category:Machine Learned Force Fields]][[Category: Alpha]] | ||
Revision as of 07:12, 23 August 2021
ML_CDOUB = [real]
Default: ML_CDOUB = 2.0
Description: This flag controls the necessity of DFT calculations in the machine learning force field method.
If at any time, the estimated errors are ML_CDOUB times larger than the Bayesian threshold, a first principles calculation is performed and a new force field is immediately generated (even if the counter for sampling is below the minimum amount of sampled structures ML_NMDINT).
Related Tags and Sections
ML_LMLFF, ML_CTIFOR, ML_NMDINT