ML ISCALE TOTEN: Difference between revisions
No edit summary |
No edit summary |
||
| Line 4: | Line 4: | ||
---- | ---- | ||
The following cases are possible: | The following cases are possible: | ||
*{{TAG|ML_FF_ISCALE_TOTEN_MB}}=1: The total energy is scaled to the total energy of the isolated atoms given by {{TAG|ML_FF_EATOM}} | *{{TAG|ML_FF_ISCALE_TOTEN_MB}}=1: The total energy is scaled to the total energy of the isolated atoms given by {{TAG|ML_FF_EATOM}}. | ||
*{{TAG|ML_FF_ISCALE_TOTEN_MB}}=2: The total energy is scaled to the average of the training data. | *{{TAG|ML_FF_ISCALE_TOTEN_MB}}=2: The total energy is scaled to the average of the training data. This is the default setting. | ||
Revision as of 12:23, 3 January 2020
ML_FF_ISCALE_TOTEN_MB = [integer]
Default: ML_FF_ISCALE_TOTEN_MB = 2
Description: This tag specifies how to scale the energy data for the many-body term in the machine learning force field method.
The following cases are possible:
- ML_FF_ISCALE_TOTEN_MB=1: The total energy is scaled to the total energy of the isolated atoms given by ML_FF_EATOM.
- ML_FF_ISCALE_TOTEN_MB=2: The total energy is scaled to the average of the training data. This is the default setting.