ML IREG: Difference between revisions

Latest revision as of 13:24, 8 April 2022

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 1: / Line 1: @@
-{{TAGDEF|ML_FF_IREG_MB|[integer]|2}}
+{{DISPLAYTITLE:ML_IREG}}
+{{TAGDEF|ML_IREG|[integer]|2}}
-Description:
+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:
+*{{TAG|ML_IREG}}=1: The (initial) precision ({{TAG|ML_SIGV0}}) and noise ({{TAG|ML_SIGW0}}) parameters are kept constant.
+*{{TAG|ML_IREG}}=2: The parameters are optimized (default).
-== Related Tags and Sections ==
+For the optimization of the noise parameter <math>\sigma_{\mathrm{v}}^{2}</math> see [[Machine learning force fields: Theory#Bayesian error estimation|this section]].
-{{sc|ML_FF_IREG_MB|Examples|Examples that use this tag}}
+== Related tags and articles ==
+{{TAG|ML_LMLFF}}, {{TAG|ML_SIGV0}}, {{TAG|ML_SIGW0}}
+{{sc|ML_IREG|Examples|Examples that use this tag}}
 ----
-[[Category:INCAR]][[Category:Machine Learning]][[Category:Machine Learned Force Fields]]
+[[Category:INCAR tag]][[Category:Machine-learned force fields]]