ML SCLC CTIFOR: Difference between revisions
No edit summary |
No edit summary |
||
| Line 8: | Line 8: | ||
The default value of 0.8 was set by us empirically in dependence of default values for other input parameters. | The default value of 0.8 was set by us empirically in dependence of default values for other input parameters. | ||
If this value is decreased, often the initial learning efficiency is much improved. This applies in particular to liquid and polymeric system, with a large configurational space. | If this value is decreased, often the initial learning efficiency is much improved. This applies in particular to liquid and polymeric system, with a large configurational space. Good values are around 0.5 for such systems. | ||
== Related tags and articles == | == Related tags and articles == | ||
Revision as of 18:18, 22 February 2023
ML_IREG = [real]
Default: ML_IREG = 0.8
Description: Sets fraction by which the Bayesian threshold for the maximum forces is lowered in the selection of local reference calculations.
At every sampling step each atom with it's environment is chosen as a local reaference configuration is chosen if it's predicted error in the force is larger than the Bayesian threshold for the maximum forces (ML_CTIFOR). ML_SCLC_CTIFOR lowers the threshold by multiplying it to ML_CTIFOR, but it doesn't effect the decision whether a sampling step (ab-initio calculation) is carried out or not, since the decision for sampling is done previously in a separate step.
The default value of 0.8 was set by us empirically in dependence of default values for other input parameters.
If this value is decreased, often the initial learning efficiency is much improved. This applies in particular to liquid and polymeric system, with a large configurational space. Good values are around 0.5 for such systems.
Related tags and articles
ML_LMLFF, ML_CTIFOR, ML_CX, ML_EPS_LOW