ML SION1: Difference between revisions
No edit summary |
No edit summary |
||
| Line 1: | Line 1: | ||
{{TAGDEF|ML_SION1|[real]|0.5}} | {{TAGDEF|ML_SION1|[real]|0.5}} | ||
Description: This tag specifies the width <math>\sigma_\text{atom}</math> of the Gaussian functions used for broadening the atomic distributions | Description: This tag specifies the width <math>\sigma_\text{atom}</math> of the Gaussian functions used for broadening the atomic distributions of the radial descriptor <math>\rho^{(2)}_i(r)</math> within the machine learning force field method (see [[Machine learning force field: Theory#Descriptors|this section]]). | ||
---- | ---- | ||
Revision as of 20:38, 10 October 2021
ML_SION1 = [real]
Default: ML_SION1 = 0.5
Description: This tag specifies the width [math]\displaystyle{ \sigma_\text{atom} }[/math] of the Gaussian functions used for broadening the atomic distributions of the radial descriptor [math]\displaystyle{ \rho^{(2)}_i(r) }[/math] within the machine learning force field method (see this section).
The unit of ML_SION1 is [math]\displaystyle{ \AA }[/math].
| Our test calculations indicate that ML_SION1 = ML_SION2 results in an optimal training performance. Furthermore, a value of 0.5 was found to be a good default value for both. However, the best choice is system-dependent, careful testing may improve machine learning results. |
Related Tags and Sections
ML_LMLFF, ML_SION2, ML_RCUT1, ML_RCUT2, ML_MRB1, ML_MRB2