ML NRANK SPARSDES: Difference between revisions
No edit summary |
No edit summary |
||
| Line 1: | Line 1: | ||
{{DISPLAYTITLE:ML_NRANK_SPARSDES}} | |||
{{TAGDEF|ML_NRANK_SPARSDES|[integer]|5}} | {{TAGDEF|ML_NRANK_SPARSDES|[integer]|5}} | ||
| Line 7: | Line 8: | ||
For details on how to use the sparsification see the tag {{TAG|ML_LSPARSDES}}. | For details on how to use the sparsification see the tag {{TAG|ML_LSPARSDES}}. | ||
== Related | == Related tags and articles == | ||
{{TAG|ML_LMLFF}}, {{TAG|ML_LSPARSDES}}, {{TAG|ML_RDES_SPARSDES}} | {{TAG|ML_LMLFF}}, {{TAG|ML_LSPARSDES}}, {{TAG|ML_RDES_SPARSDES}} | ||
{{sc|ML_EPS_LOW|Examples|Examples that use this tag}} | {{sc|ML_EPS_LOW|Examples|Examples that use this tag}} | ||
[[Category:INCAR]][[Category:Machine Learning]][[Category:Machine Learned Force Fields | [[Category:INCAR tag]][[Category:Machine Learning]][[Category:Machine Learned Force Fields]] | ||
Revision as of 07:38, 7 April 2022
ML_NRANK_SPARSDES = [integer]
Default: ML_NRANK_SPARSDES = 5
Description: This tag sets the number of highest eigenvalues to which the correlation is measured within the angular descriptor sparsification (within the machine learning force field method).
For details on the theory of angular descriptor sparsification see here.
For details on how to use the sparsification see the tag ML_LSPARSDES.