ML MCONF NEW - Revision history

Singraber at 07:56, 24 October 2025

2025-10-24T07:56:03Z

← Older revision		Revision as of 07:56, 24 October 2025
Line 7:		Line 7:

	The use of this tag in combination with the learning algorithms is described here: [[Machine learning force field calculations: Basics#Sampling of training data and local reference configurations\|here]].		The use of this tag in combination with the learning algorithms is described here: [[Machine learning force field calculations: Basics#Sampling of training data and local reference configurations\|here]].
	If force fields are reparameterized ({{~~TAGO~~\|ML_MODE\|select}}), calculations are usually more efficient if this parameter is increased to values around 10-16 and setting {{~~TAGO~~\|ML_CDOUB\|4}}. This is particularly relevant if the ML_AB file is large.		If force fields are reparameterized ({{TAG\|ML_MODE\|select}}), calculations are usually more efficient if this parameter is increased to values around 10-16 and setting {{TAG\|ML_CDOUB\|4}}. This is particularly relevant if the ML_AB file is large.

	== Related tags and articles ==		== Related tags and articles ==

Singraber at 15:32, 19 October 2023

2023-10-19T15:32:50Z

← Older revision		Revision as of 15:32, 19 October 2023
Line 7:		Line 7:

	The use of this tag in combination with the learning algorithms is described here: [[Machine learning force field calculations: Basics#Sampling of training data and local reference configurations\|here]].		The use of this tag in combination with the learning algorithms is described here: [[Machine learning force field calculations: Basics#Sampling of training data and local reference configurations\|here]].
	If force fields are reparameterized ({{TAGO\|ML_MODE\|select}}), calculations are usually more efficient if this parameter is increased to values around 10-16 and setting {{~~TAG~~\|ML_CDOUB}}=4. This is particularly relevant if the ML_AB file is large.		If force fields are reparameterized ({{TAGO\|ML_MODE\|select}}), calculations are usually more efficient if this parameter is increased to values around 10-16 and setting {{TAGO\|ML_CDOUB\|4}}. This is particularly relevant if the ML_AB file is large.

	== Related tags and articles ==		== Related tags and articles ==

Singraber at 15:32, 19 October 2023

2023-10-19T15:32:29Z

← Older revision		Revision as of 15:32, 19 October 2023
Line 7:		Line 7:

	The use of this tag in combination with the learning algorithms is described here: [[Machine learning force field calculations: Basics#Sampling of training data and local reference configurations\|here]].		The use of this tag in combination with the learning algorithms is described here: [[Machine learning force field calculations: Basics#Sampling of training data and local reference configurations\|here]].
	If force fields are reparameterized ({{TAGO\|~~ML_ISTART~~\|select}}), calculations are usually more efficient if this parameter is increased to values around 10-16 and setting {{TAG\|ML_CDOUB}}=4. This is particularly relevant if the ML_AB file is large.		If force fields are reparameterized ({{TAGO\|ML_MODE\|select}}), calculations are usually more efficient if this parameter is increased to values around 10-16 and setting {{TAG\|ML_CDOUB}}=4. This is particularly relevant if the ML_AB file is large.

	== Related tags and articles ==		== Related tags and articles ==

Singraber at 14:47, 19 October 2023

2023-10-19T14:47:35Z

← Older revision		Revision as of 14:47, 19 October 2023
Line 7:		Line 7:

	The use of this tag in combination with the learning algorithms is described here: [[Machine learning force field calculations: Basics#Sampling of training data and local reference configurations\|here]].		The use of this tag in combination with the learning algorithms is described here: [[Machine learning force field calculations: Basics#Sampling of training data and local reference configurations\|here]].
	If force fields are reparameterized ({{~~TAG~~\|ML_ISTART}}=3), calculations are usually more efficient if this parameter is increased to values around 10-16 and setting {{TAG\|ML_CDOUB}}=4. This is particularly relevant if the ML_AB file is large.		If force fields are reparameterized ({{TAGO\|ML_ISTART\|select}}), calculations are usually more efficient if this parameter is increased to values around 10-16 and setting {{TAG\|ML_CDOUB}}=4. This is particularly relevant if the ML_AB file is large.

	== Related tags and articles ==		== Related tags and articles ==

Kresse at 08:54, 26 August 2022

2022-08-26T08:54:00Z

← Older revision		Revision as of 08:54, 26 August 2022
Line 7:		Line 7:

	The use of this tag in combination with the learning algorithms is described here: [[Machine learning force field calculations: Basics#Sampling of training data and local reference configurations\|here]].		The use of this tag in combination with the learning algorithms is described here: [[Machine learning force field calculations: Basics#Sampling of training data and local reference configurations\|here]].
	If force fields are reparameterized ({{TAG\|ML_ISTART}}=3), calculations are usually more efficient, if this parameter is increased to values around 10-16 ~~in particular,~~ if the ML_AB ~~files are~~ large.		If force fields are reparameterized ({{TAG\|ML_ISTART}}=3), calculations are usually more efficient if this parameter is increased to values around 10-16 and setting {{TAG\|ML_CDOUB}}=4. This is particularly relevant if the ML_AB file is large.

	== Related tags and articles ==		== Related tags and articles ==

Kresse at 08:42, 26 August 2022

2022-08-26T08:42:26Z

← Older revision		Revision as of 08:42, 26 August 2022
Line 7:		Line 7:

	The use of this tag in combination with the learning algorithms is described here: [[Machine learning force field calculations: Basics#Sampling of training data and local reference configurations\|here]].		The use of this tag in combination with the learning algorithms is described here: [[Machine learning force field calculations: Basics#Sampling of training data and local reference configurations\|here]].
	If force fields are reparameterized ({{TAG\|ML_ISTART}}=3), calculations are usually more efficient, if this parameter is increased.		If force fields are reparameterized ({{TAG\|ML_ISTART}}=3), calculations are usually more efficient, if this parameter is increased to values around 10-16 in particular, if the ML_AB files are large.

	== Related tags and articles ==		== Related tags and articles ==

Kresse: Documented that increasing the parameter for ML_ISTART=3 increases efficiency.

2022-07-29T09:25:50Z

Documented that increasing the parameter for ML_ISTART=3 increases efficiency.

← Older revision		Revision as of 09:25, 29 July 2022
Line 7:		Line 7:

	The use of this tag in combination with the learning algorithms is described here: [[Machine learning force field calculations: Basics#Sampling of training data and local reference configurations\|here]].		The use of this tag in combination with the learning algorithms is described here: [[Machine learning force field calculations: Basics#Sampling of training data and local reference configurations\|here]].
	If force fields are reparameterized, calculations are usually more efficient, if this parameter is increased.		If force fields are reparameterized ({{TAG\|ML_ISTART}}=3), calculations are usually more efficient, if this parameter is increased.

	== Related tags and articles ==		== Related tags and articles ==

Kresse at 09:24, 29 July 2022

2022-07-29T09:24:13Z

← Older revision		Revision as of 09:24, 29 July 2022
Line 4:		Line 4:
	Description: This tag sets the number of configurations that are stored temporarily as candidates for the training data in the machine learning force field method.		Description: This tag sets the number of configurations that are stored temporarily as candidates for the training data in the machine learning force field method.
	----		----
	{{NB\|warning\|This value is close to optimal for on-the-fly learning, and should usually not be changed~~. If force fields are reparameterized, calculations are usually more efficient, if this parameter is increased~~.}}		{{NB\|warning\|This value is close to optimal for on-the-fly learning, and should usually not be changed. }}

	The use of this tag in combination with the learning algorithms is described here: [[Machine learning force field calculations: Basics#Sampling of training data and local reference configurations\|here]].		The use of this tag in combination with the learning algorithms is described here: [[Machine learning force field calculations: Basics#Sampling of training data and local reference configurations\|here]].
			If force fields are reparameterized, calculations are usually more efficient, if this parameter is increased.

	== Related tags and articles ==		== Related tags and articles ==

Kresse at 09:23, 29 July 2022

2022-07-29T09:23:25Z

← Older revision		Revision as of 09:23, 29 July 2022
Line 4:		Line 4:
	Description: This tag sets the number of configurations that are stored temporarily as candidates for the training data in the machine learning force field method.		Description: This tag sets the number of configurations that are stored temporarily as candidates for the training data in the machine learning force field method.
	----		----
	{{NB\|warning\|This value is ~~empirically set~~ and should usually not be ~~touched~~.}}		{{NB\|warning\|This value is close to optimal for on-the-fly learning, and should usually not be changed. If force fields are reparameterized, calculations are usually more efficient, if this parameter is increased.}}

	The ~~usage~~ of this tag in combination with the learning algorithms is described here: [[Machine learning force field calculations: Basics#Sampling of training data and local reference configurations\|here]].		The use of this tag in combination with the learning algorithms is described here: [[Machine learning force field calculations: Basics#Sampling of training data and local reference configurations\|here]].

	== Related tags and articles ==		== Related tags and articles ==

Karsai: /* Related tags and articles */

2022-04-08T13:27:48Z

← Older revision		Revision as of 13:27, 8 April 2022
Line 14:		Line 14:
	{{TAG\|ML_LMLFF}}, {{TAG\|ML_MCONF}}, {{TAG\|ML_CTIFOR}}, {{TAG\|ML_CDOUB}}		{{TAG\|ML_LMLFF}}, {{TAG\|ML_MCONF}}, {{TAG\|ML_CTIFOR}}, {{TAG\|ML_CDOUB}}

	[[Category:INCAR tag]][[Category:Machine ~~Learning]][[Category:Machine Learned Force Fields~~]]		[[Category:INCAR tag]][[Category:Machine-learned force fields]]