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
Line 4: Line 4:
 
----
 
----
 
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 (default).
 
*{{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|On-the-fly machine learning force field generation using Bayesian linear regression}}.
  
 
== Related Tags and Sections ==
 
== Related Tags and Sections ==

Revision as of 18:11, 19 May 2019

ML_FF_IREG_MB = [integer]
Default: ML_FF_IREG_MB = 2 

Description: This tag specifies whether the noise 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: On-the-fly machine learning force field generation using Bayesian linear regression.

Related Tags and Sections

ML_FF_LMLFF, ML_FF_SIGV0_MB, ML_FF_SIGW0_MB

Examples that use this tag