ML SIGV0: Difference between revisions
No edit summary |
No edit summary |
||
Line 1: | Line 1: | ||
{{TAGDEF|ML_FF_SIGV0_MB|[real]|1.0}} | {{TAGDEF|ML_FF_SIGV0_MB|[real]|1.0}} | ||
Description: This flag sets the initial | Description: This flag sets the initial reversed and squared noise parameter <math>\frac{1}{\sigma_{\mathrm{v}}^{2}}</math> in the machine learning force field method. | ||
---- | ---- | ||
For the optimization of the optimization of the reverse noise parameter <math>\frac{1}{\sigma_{\mathrm{v}}^{2}}</math> see following section: | For the optimization of the optimization of the reverse and squared noise parameter <math>\frac{1}{\sigma_{\mathrm{v}}^{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}}. | ||
Revision as of 13:15, 2 December 2019
ML_FF_SIGV0_MB = [real]
Default: ML_FF_SIGV0_MB = 1.0
Description: This flag sets the initial reversed and squared noise parameter in the machine learning force field method.
For the optimization of the optimization of the reverse 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_SIGW0_MB