Requests for technical support from the VASP group should be posted in the VASP-forum.

Difference between revisions of "ML FF IREG MB"

From Vaspwiki
Jump to navigationJump to search
 
(6 intermediate revisions by the same user not shown)
Line 1: Line 1:
 
{{TAGDEF|ML_FF_IREG_MB|[integer]|2}}
 
{{TAGDEF|ML_FF_IREG_MB|[integer]|2}}
  
Description: This tag specifies whether the noise parameters are kept constant or not in the machine learning force field method.
+
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:
 
The following cases are possible for this tag:
*{{TAG|ML_FF_IREG_MB}}=1: The precision ({{TAG|ML_FF_SIGV0_MB}}) and noise ({{TAG|ML_FF_SIGW0_MB}}) parameters are kept constant.
+
*{{TAG|ML_FF_IREG_MB}}=1: The (initial) precision ({{TAG|ML_FF_SIGV0_MB}}) and noise ({{TAG|ML_FF_SIGW0_MB}}) parameters are kept constant.
*{{TAG|ML_FF_IREG_MB}}=2: The parameters are optimized.
+
*{{TAG|ML_FF_IREG_MB}}=2: The parameters are optimized (default).
 +
 
 +
For the optimization of the noise parameter <math>\sigma_{\mathrm{v}}^{2}</math> see following section:
 +
{{TAG|Machine learning force fields: Theory}}.
  
 
== Related Tags and Sections ==
 
== Related Tags and Sections ==
{{TAG|ML_FF_MLFF}}, {{TAG|ML_FF_SIGV0_MB}}, {{TAG|ML_FF_SIGW0_MB}}
+
{{TAG|ML_FF_LMLFF}}, {{TAG|ML_FF_SIGV0_MB}}, {{TAG|ML_FF_SIGW0_MB}}
  
 
{{sc|ML_FF_IREG_MB|Examples|Examples that use this tag}}
 
{{sc|ML_FF_IREG_MB|Examples|Examples that use this tag}}
 
----
 
----
  
[[Category:INCAR]][[Category:Machine Learning]][[Category:Machine Learned Force Fields]][[Category:VASP6]]
+
[[Category:INCAR]][[Category:Machine Learning]][[Category:Machine Learned Force Fields]][[Category: Alpha]]

Latest revision as of 15:16, 29 February 2020

ML_FF_IREG_MB = [integer]
Default: ML_FF_IREG_MB = 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:

For the optimization of the noise parameter see following section: Machine learning force fields: Theory.

Related Tags and Sections

ML_FF_LMLFF, ML_FF_SIGV0_MB, ML_FF_SIGW0_MB

Examples that use this tag