ML SIGW0: Difference between revisions
No edit summary |
No edit summary |
||
| Line 13: | Line 13: | ||
---- | ---- | ||
[[Category:INCAR]][[Category:Machine Learning]][[Category:Machine Learned Force Fields | [[Category:INCAR]][[Category:Machine Learning]][[Category:Machine Learned Force Fields]] | ||
Revision as of 11:04, 30 January 2020
ML_FF_SIGW0_MB = [real]
Default: ML_FF_SIGW0_MB = 1.0
Description: This flag sets the initial reversed and squared precision parameter [math]\displaystyle{ \frac{1}{\sigma_{\mathrm{w}}^{2}} }[/math] in the machine learning force field method.
For the optimization of the reversed and squared noise parameter [math]\displaystyle{ \frac{1}{\sigma_{\mathrm{w}}^{2}} }[/math] see following section: On-the-fly machine learning force field generation using Bayesian linear regression.
Related Tags and Sections
ML_FF_LMLFF, ML_FF_IREG_MB, ML_FF_SIGV0_MB