Search results

  • ML LMLFF (category Machine-learned force fields)
    control tag which enables/disables the use of machine learning force fields. If ML_LMLFF = .FALSE. machine learning force fields are disabled and all related...
    1 KB (151 words) - 14:46, 19 October 2023
  • ML MODE (category Machine-learned force fields)
    initio calculations are performed and no learning is executed. This setting is typically used when the machine learning force field is considered mature and...
    9 KB (987 words) - 22:21, 19 October 2023
  • on that structure. Fig. 1: On-the-fly machine learning force field generation scheme. To obtain the machine-learning force field several structure datasets...
    35 KB (7,244 words) - 13:25, 24 April 2024
  • Machine learning force field calculations: Basics (category Machine-learned force fields)
    The machine-learned force fields (MLFF) feature of VASP allows you to generate, improve, modify and apply force fields based on machine learning techniques...
    11 KB (1,403 words) - 13:18, 17 May 2023
  • ML LOGFILE (category Machine-learned force fields) (section Machine learning setup)
    initio log output in the OUTCAR and OSZICAR files for machine learning VASP runs. The machine learning log file is split into multiple sections, visually...
    21 KB (2,342 words) - 15:01, 19 October 2023
  • theory, pseudopotentials, projector-augmented-wave formalism, phonons, machine learning force fields, hybrid functionals, GW approximation, etc. Calculation...
    9 KB (29 words) - 13:21, 19 March 2024
  • ML CTIFOR (category Machine-learned force fields)
    estimation on the force within the machine learning force field method. The use of this tag in combination with the learning algorithms is described here: here...
    2 KB (218 words) - 06:46, 13 October 2023
  • ML IALGO LINREG (category Machine-learned force fields)
    equations in the ridge regression method for machine learning. In the ridge regression method for machine learning one needs to solve for the unknown weights...
    4 KB (480 words) - 15:52, 3 July 2023
  • ML LSPARSDES (category Machine-learned force fields)
    Specifies whether angular-descriptor sparsification is enabled within the machine learning force field method. To use the sparsification of angular descriptors...
    2 KB (235 words) - 14:00, 20 March 2024
  • ML MCONF NEW (category Machine-learned force fields)
    candidates for the training data in the machine learning force field method. The use of this tag in combination with the learning algorithms is described here: here...
    1 KB (101 words) - 15:32, 19 October 2023
  • ML EPS LOW (category Machine-learned force fields)
    in the sparsification of local reference configurations within the machine learning force fields. This value sets the threshold for the eigenvalues that...
    2 KB (181 words) - 11:42, 15 May 2023
  • ML MHIS (category Machine-learned force fields)
    in memory to determine the threshold for the Bayesian error in the machine learning force field method for ML_ICRITERIA=1. For ML_ICRITERIA=2, the history...
    2 KB (219 words) - 09:49, 8 November 2023
  • to the OSZICAR file is also written for force-field only steps when machine learning force fields are used. In that case the E0 entry contains the same...
    3 KB (545 words) - 06:42, 8 March 2022
  • ML CDOUB (category Machine-learned force fields)
    "enforced" DFT calculations within the machine learning force field method. The usage of this tag in combination with the learning algorithms is described here:...
    1,007 bytes (100 words) - 14:37, 19 October 2023
  • ML NRANK SPARSDES (category Machine-learned force fields)
    is measured within the angular descriptor sparsification (within the machine learning force field method). This tag usually does not need to be changed by...
    862 bytes (87 words) - 14:01, 20 March 2024
  • ML ISTART (category Machine-learned force fields)
    start from scratch, prediction-only,...) of the machine learning force fields method. If the machine learning force fields method is enabled via ML_LMLFF =...
    6 KB (819 words) - 14:40, 19 October 2023
  • ML MB (category Machine-learned force fields)
    reference configurations (i.e. basis functions in the kernel) in the machine learning force field method. The defaults for ML_MB are different for each different...
    3 KB (479 words) - 17:11, 15 February 2024
  • ML AB (category Machine-learned force fields)
    used as input (with file name ML_AB) and output (ML_ABN) within the machine learning force field method. It contains the collection of ab initio data from...
    16 KB (1,702 words) - 08:32, 20 October 2023
  • charge mixing information from the previous ionic steps. (ii) During machine learning, the first-principles calculations are often bypassed for hundreds...
    4 KB (512 words) - 09:43, 18 October 2023
  • ML MRB1 (category Machine-learned force fields)
    descriptor ρ i ( 2 ) ( r ) {\displaystyle \rho _{i}^{(2)}(r)} within the machine learning force field method. The radial descriptor is constructed from ρ i (...
    1 KB (283 words) - 08:06, 9 May 2023
  • ML SION1 (category Machine-learned force fields)
    descriptor ρ i ( 2 ) ( r ) {\displaystyle \rho _{i}^{(2)}(r)} within the machine learning force field method. The radial descriptor is constructed from ρ i (...
    2 KB (262 words) - 13:31, 8 April 2022
  • ML CX (category Machine-learned force fields)
    (ML_CTIFOR) is updated within the machine learning force field methods. The use of this tag in combination with the learning algorithms is described here:...
    2 KB (326 words) - 15:24, 17 September 2022
  • ML CSLOPE (category Machine-learned force fields)
    Bayesian error estimation in the machine learning force field method. The usage of this tag in combination with the learning algorithms is described here:...
    915 bytes (106 words) - 13:21, 8 April 2022
  • ML CSIG (category Machine-learned force fields)
    Bayesian error estimation in the machine learning force field method. The usage of this tag in combination with the learning algorithms is described here:...
    948 bytes (110 words) - 13:21, 8 April 2022
  • ML MCONF (category Machine-learned force fields)
    number of structures stored in memory that are used for training in the machine learning force field method. The defaults for ML_MCONF are different for each...
    2 KB (291 words) - 09:22, 28 April 2023
  • ML MRB2 (category Machine-learned force fields)
    radial basis functions used to expand the angular descriptor within the machine learning force field method. The angular descriptor is constructed from ρ i...
    2 KB (424 words) - 11:56, 31 March 2023
  • ML RCUT2 (category Machine-learned force fields)
    descriptor ρ i ( 3 ) ( r ) {\displaystyle \rho _{i}^{(3)}(r)} in the machine learning force field method. The unit of the cut-off radius is Å {\displaystyle...
    2 KB (378 words) - 13:35, 9 May 2023
  • ML SION2 (category Machine-learned force fields)
    descriptor ρ i ( 3 ) ( r ) {\displaystyle \rho _{i}^{(3)}(r)} within the machine learning force field method. The angular descriptor is constructed from ρ i...
    2 KB (310 words) - 13:31, 8 April 2022
  • ML W1 (category Machine-learned force fields)
    {\displaystyle \beta } for the radial (and angular) descriptor within the machine learning force field method (see this section). The weight for the angular descriptor...
    1 KB (155 words) - 13:31, 8 April 2022
  • ML IREG (category Machine-learned force fields)
    whether the regularization parameters are kept constant or not in the machine learning force field method. The following cases are possible for this tag:...
    805 bytes (88 words) - 13:24, 8 April 2022
  • Best practices for machine-learned force fields (category Machine-learned force fields) (section Monitoring on-the-fly learning)
    computation during on-the-fly learning: Do not set MAXMIX>0 when using force fields for machine learning. During machine learning, first-principles calculations...
    59 KB (7,278 words) - 07:15, 11 April 2024
  • ML WTIFOR (category Machine-learned force fields)
    weight for the scaling of the forces in the training data within the machine learning force field method. ML_IWEIGHT, ML_WTOTEN, ML_WTIFOR, ML_WTSIF form...
    1,016 bytes (123 words) - 13:31, 8 April 2022
  • ML WTSIF (category Machine-learned force fields)
    weight for the scaling of the stress in the training data within the machine learning force field method. ML_IWEIGHT, ML_WTOTEN, ML_WTIFOR, ML_WTSIF form...
    1,006 bytes (122 words) - 13:32, 8 April 2022
  • ML SIGW0 (category Machine-learned force fields)
    s_{\mathrm {w} }} (see here for definition) for the fitting in the machine learning force field method. The default value for ML_MODE=REFIT works reliable...
    1 KB (124 words) - 16:05, 3 July 2023
  • ML AFILT2 (category Machine-learned force fields)
    filtering parameter for the angular filtering for ML_IAFILT2 in the machine learning force field method. This tag is only used if ML_LAFILT2=.TRUE. and...
    817 bytes (129 words) - 13:19, 8 April 2022
  • ML DESC TYPE (category Machine-learned force fields)
    tag selects the descriptor type of the three-body descriptor used in machine learning force fields. This tag selects how the three-body descriptor is calculated...
    4 KB (636 words) - 09:16, 26 April 2024
  • ML ISCALE TOTEN (category Machine-learned force fields)
    Description: This tag specifies how to scale the energy data in the machine learning force field method. The following cases are possible: ML_ISCALE_TOTEN...
    669 bytes (84 words) - 10:02, 19 February 2024
  • ML ICRITERIA (category Machine-learned force fields)
    how the Bayesian error threshold (ML_CTIFOR) is updated within the machine learning force field method. ML_CTIFOR determines whether a first-principles...
    5 KB (696 words) - 09:09, 14 April 2023
  • ML SIGV0 (category Machine-learned force fields)
    s_{\mathrm {v} }} (see here for definition) for the fitting in the machine learning force field method. If the regularization needs to be controlled manually...
    975 bytes (112 words) - 16:05, 3 July 2023
  • ML LCOUPLE (category Machine-learned force fields)
    activated in order to calculate the chemical potentials within the machine learning force field method. In thermodynamic integration a coupling parameter...
    4 KB (619 words) - 11:07, 11 November 2023
  • ML FFN (category Machine-learned force fields)
    This binary file contains a knewly created force field from machine learning runs with the options ML_MODE=train, refit or select. It's structure is identical...
    2 KB (247 words) - 13:38, 5 May 2023
  • ML IAFILT2 (category Machine-learned force fields)
    Description: This tag specifies the type of angular filtering used in the machine learning force field method. Fig. 1: Square of filtering function. This tag...
    2 KB (303 words) - 08:41, 1 August 2022
  • ML LAFILT2 (category Machine-learned force fields)
    tag specifies whether angular filtering is applied or not within the machine learning force field method. For the desciption of the filters please see: ML_IAFILT2...
    620 bytes (58 words) - 13:24, 8 April 2022
  • ML RCOUPLE (category Machine-learned force fields)
    parameter for the calculation of the chemical potential within the machine learning force field method. For thermodynamic integration calculations please...
    563 bytes (59 words) - 13:30, 8 April 2022
  • ML ICOUPLE (category Machine-learned force fields)
    parameter is introduced to calculate the chemical potential within the machine learning force field method. Atom are ordered according to the POSCAR file and...
    662 bytes (69 words) - 13:23, 8 April 2022
  • ML NATOM COUPLED (category Machine-learned force fields)
    parameter is introduced to calculate the chemical potential within the machine learning force field method. For thermodynamic integration calculations please...
    596 bytes (62 words) - 13:29, 8 April 2022
  • ML IWEIGHT (category Machine-learned force fields)
    normalizing and weighting the energies, forces, and stresses in the machine learning force field method. To achieve optimal training it is important to...
    4 KB (425 words) - 09:48, 19 April 2023
  • the bug report. 6.4.1 6.4.0 2023-03-07 Output of memory estimate in machine learning force fields is wrong for SVD refitting: The SVD algorithm (ML_IALGO_LINREG=3...
    18 KB (27 words) - 19:20, 10 April 2024
  • ML NMDINT (category Machine-learned force fields)
    to get training samples in the machine learning force field method. The usage of this tag in combination with the learning algorithms is described here:...
    1 KB (115 words) - 09:47, 8 November 2023
  • ML LMAX2 (category Machine-learned force fields)
    spherical harmonics used to expand atomic distributions within the machine learning force field method. To construct an atomic environment descriptor the...
    2 KB (332 words) - 08:11, 9 May 2023
View (previous 50 | ) (20 | 50 | 100 | 250 | 500)