ML IREG: Difference between revisions

Revision as of 10:52, 30 January 2020

ML_FF_IREG_MB = [integer]
Default: ML_FF_IREG_MB = 2

Description: This tag specifies whether the regularization parameters are kept constant or not in the machine learning force field method.

The following cases are possible for this tag:

ML_FF_IREG_MB=1: The (initial) precision (ML_FF_SIGV0_MB) and noise (ML_FF_SIGW0_MB) parameters are kept constant.
ML_FF_IREG_MB=2: The parameters are optimized (default).

For the optimization of the noise parameter $\sigma_{\mathrm{v}}^{2}$ see following section: Machine learning force fields: Theory.

Revision as of 07:48, 15 January 2020 (view source) Karsai (talk \| contribs) No edit summary ← Older edit		Revision as of 10:52, 30 January 2020 (view source) Karsai (talk \| contribs) No edit summary Newer edit →
Line 16:		Line 16:
	----		----

	[[Category:INCAR]][[Category:Machine Learning]][[Category:Machine Learned Force Fields~~]][[Category:VASP6~~]]		[[Category:INCAR]][[Category:Machine Learning]][[Category:Machine Learned Force Fields]]