ML SIGV0: Difference between revisions
No edit summary |
No edit summary |
||
| Line 9: | Line 9: | ||
== Related tags and sections == | == Related tags and sections == | ||
{{TAG|ML_LMLFF}}, {{TAG|ML_IREG}}, {{TAG|ML_SIGW0}} | {{TAG|ML_LMLFF}}, {{TAG|ML_IREG}}, {{TAG|ML_SIGW0}}, {{TAG|ML_IALGO_LINREG}} | ||
{{sc|ML_SIGV0|Examples|Examples that use this tag}} | {{sc|ML_SIGV0|Examples|Examples that use this tag}} | ||
Revision as of 15:46, 3 July 2023
ML_SIGV0 = [real]
Default: ML_SIGV0 = 1.0
Description: This flag sets the noise parameter [math]\displaystyle{ s_{\mathrm{v}} }[/math] for the fitting in the machine learning force field method.
If the regularization needs to be controlled manually, like e.g. in the fitting via singular value decomposition (ML_IALGO_LINREG=4), the best is to keep this parameter constant at 1 and control the regularization via the precision parameter [math]\displaystyle{ s_{\mathrm{w}} }[/math] (see ML_SIGW0).
For the theory of this regularization parameter see this section.
Related tags and sections
ML_LMLFF, ML_IREG, ML_SIGW0, ML_IALGO_LINREG