ML SIGW0: Difference between revisions

Revision as of 09:58, 5 October 2021

ML_SIGW0 = [real]
Default: ML_SIGW0 = 1.0

Description: This flag sets the initial reversed and squared precision parameter $\frac{1}{\sigma_{\mathrm{w}}^{2}}$ in the machine learning force field method.

For the optimization of the reversed and squared noise parameter $\frac{1}{\sigma_{\mathrm{w}}^{2}}$ see following section: Machine learning force field: Theory.

Related Tags and Sections

ML_LMLFF, ML_IREG, ML_SIGV0

Examples that use this tag

@@ Line 5: / Line 5: @@
 For the optimization of the reversed and squared noise parameter <math>\frac{1}{\sigma_{\mathrm{w}}^{2}}</math> see following section:
-{{TAG|On-the-fly machine learning force field generation using Bayesian linear regression}}.
+{{TAG|Machine learning force field: Theory}}.
 == Related Tags and Sections ==