Pre-trained and fine-tuned ANI models for: Transfer learning for chemically accurate interatomic neural network potentials

DOI

Pre-trained and fine-tuned ANI models using the Gaussian Moments Neural Network (GM-NN) approach. Code for GM-NN implemented within the Tensorflow framework, including the respective documentation and tutorials, can be found on GitLab.

The data represents TensorFlow v2 checkpoints and stores the metadata for the checkpoint and parameters for the model. Checkpoints can be read by the source code provided on GitLab. A detailed description for reproducing the results and employing pre-trained and fine-tuned models during a simulation is provided in the GM-NN Documentation.

Identifier
DOI https://doi.org/10.18419/darus-3299
Related Identifier IsCitedBy https://doi.org/10.1039/D2CP05793J
Metadata Access https://darus.uni-stuttgart.de/oai?verb=GetRecord&metadataPrefix=oai_datacite&identifier=doi:10.18419/darus-3299
Provenance
Creator Zaverkin, Viktor ORCID logo; Holzmüller, David ORCID logo; Bonfirraro, Luca ORCID logo; Kästner, Johannes ORCID logo
Publisher DaRUS
Contributor Zaverkin, Viktor; Kästner, Johannes
Publication Year 2023
Funding Reference DFG EXC 2075 - 390740016 ; DFG INST 40/575-1 FUGG (JUSTUS 2 cluster) ; AISA
Rights CC BY 4.0; info:eu-repo/semantics/openAccess; http://creativecommons.org/licenses/by/4.0
OpenAccess true
Contact Zaverkin, Viktor (Universität Stuttgart); Kästner, Johannes (Universität Stuttgart)
Representation
Resource Type Dataset
Format application/octet-stream; text/plain; charset=US-ASCII; text/plain
Size 331; 216; 255; 370; 34; 11330168; 2059; 1250; 1218; 207856; 384666; 209250; 384749; 384571; 386259; 386163; 207855
Version 1.0
Discipline Chemistry; Natural Sciences; Physics