ML IREG: Difference between revisions

Revision as of 20:57, 11 October 2021

ML_IREG = [integer]
Default: ML_IREG = 2

Description: This tag specifies whether the regularization parameters are kept constant or not in the machine learning force field method.

The following cases are possible for this tag:

ML_IREG=1: The (initial) precision (ML_SIGV0) and noise (ML_SIGW0) parameters are kept constant.
ML_IREG=2: The parameters are optimized (default).

For the optimization of the noise parameter $\sigma_{\mathrm{v}}^{2}$ see this section.

@@ Line 7: / Line 7: @@
 *{{TAG|ML_IREG}}=2: The parameters are optimized (default).
-For the optimization of the noise parameter <math>\sigma_{\mathrm{v}}^{2}</math> see following section:
+For the optimization of the noise parameter <math>\sigma_{\mathrm{v}}^{2}</math> see [[Machine learning force fields: Theory#Bayesian error estimation|this section]].
-{{TAG|Machine learning force fields: Theory}}.
 == Related Tags and Sections ==