ML W1: Difference between revisions
No edit summary |
No edit summary |
||
| Line 1: | Line 1: | ||
{{DISPLAYTITLE:ML_W1}} | |||
{{TAGDEF|ML_W1|[real]|0.1}} | {{TAGDEF|ML_W1|[real]|0.1}} | ||
| Line 11: | Line 12: | ||
By default, the angular and radial descriptors are both used although the latter is weighed less. In principle a weight of 0 for one of them is selectable which allows the code to internally skip the respective computation. However, it is generally recommended to use both descriptors to achieve satisfying training results. | By default, the angular and radial descriptors are both used although the latter is weighed less. In principle a weight of 0 for one of them is selectable which allows the code to internally skip the respective computation. However, it is generally recommended to use both descriptors to achieve satisfying training results. | ||
== Related | == Related tags and articles == | ||
{{TAG|ML_LMLFF}}, {{TAG|ML_RCUT1}}, {{TAG|ML_RCUT2}}, {{TAG|ML_SION1}}, {{TAG|ML_SION2}} | {{TAG|ML_LMLFF}}, {{TAG|ML_RCUT1}}, {{TAG|ML_RCUT2}}, {{TAG|ML_SION1}}, {{TAG|ML_SION2}} | ||
| Line 17: | Line 18: | ||
---- | ---- | ||
[[Category:INCAR]][[Category:Machine Learning]][[Category:Machine Learned Force Fields | [[Category:INCAR tag]][[Category:Machine Learning]][[Category:Machine Learned Force Fields]] | ||
Revision as of 07:44, 7 April 2022
ML_W1 = [real]
Default: ML_W1 = 0.1
Description: This tag defines the weight for the radial (and angular) descriptor within the machine learning force field method (see this section).
The weight for the angular descriptor is internally computed from the weight of the radial descriptor as:
The value for ML_W1 must be chosen in the interval .
![{\displaystyle [0,1]}](https://wikimedia.org/api/rest_v1/media/math/render/svg/738f7d23bb2d9642bab520020873cccbef49768d)
By default, the angular and radial descriptors are both used although the latter is weighed less. In principle a weight of 0 for one of them is selectable which allows the code to internally skip the respective computation. However, it is generally recommended to use both descriptors to achieve satisfying training results.
Related tags and articles
ML_LMLFF, ML_RCUT1, ML_RCUT2, ML_SION1, ML_SION2