ML SIGW0: Difference between revisions
No edit summary |
No edit summary |
||
| (3 intermediate revisions by the same user not shown) | |||
| Line 1: | Line 1: | ||
{{TAGDEF|ML_FF_SIGW0_MB|[real]|1.0}} | {{TAGDEF|ML_FF_SIGW0_MB|[real]|1.0}} | ||
Description: This flag sets the initial precision parameter in the machine learning force field method. | Description: This flag sets the initial reversed and squared precision parameter <math>\frac{1}{\sigma_{\mathrm{w}}^{2}}</math> in the machine learning force field method. | ||
---- | ---- | ||
For the optimization of the noise parameter <math>\sigma_{\mathrm{w}}^{2}</math> see following section: | 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|On-the-fly machine learning force field generation using Bayesian linear regression}}. | ||
| Line 13: | Line 13: | ||
---- | ---- | ||
[[Category:INCAR]][[Category:Machine Learning]][[Category:Machine Learned Force Fields]][[Category: | [[Category:INCAR]][[Category:Machine Learning]][[Category:Machine Learned Force Fields]][[Category: Alpha]] | ||
Revision as of 15:22, 29 February 2020
ML_FF_SIGW0_MB = [real]
Default: ML_FF_SIGW0_MB = 1.0
Description: This flag sets the initial reversed and squared precision parameter in the machine learning force field method.
For the optimization of the reversed and squared 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_IREG_MB, ML_FF_SIGV0_MB