Back to Search
Start Over
Transfer learning for chemically accurate interatomic neural network potentials.
- Source :
-
Physical chemistry chemical physics : PCCP [Phys Chem Chem Phys] 2023 Feb 15; Vol. 25 (7), pp. 5383-5396. Date of Electronic Publication: 2023 Feb 15. - Publication Year :
- 2023
-
Abstract
- Developing machine learning-based interatomic potentials from ab initio electronic structure methods remains a challenging task for computational chemistry and materials science. This work studies the capability of transfer learning, in particular discriminative fine-tuning, for efficiently generating chemically accurate interatomic neural network potentials on organic molecules from the MD17 and ANI data sets. We show that pre-training the network parameters on data obtained from density functional calculations considerably improves the sample efficiency of models trained on more accurate ab initio data. Additionally, we show that fine-tuning with energy labels alone can suffice to obtain accurate atomic forces and run large-scale atomistic simulations, provided a well-designed fine-tuning data set. We also investigate possible limitations of transfer learning, especially regarding the design and size of the pre-training and fine-tuning data sets. Finally, we provide GM-NN potentials pre-trained and fine-tuned on the ANI-1x and ANI-1ccx data sets, which can easily be fine-tuned on and applied to organic molecules.
Details
- Language :
- English
- ISSN :
- 1463-9084
- Volume :
- 25
- Issue :
- 7
- Database :
- MEDLINE
- Journal :
- Physical chemistry chemical physics : PCCP
- Publication Type :
- Academic Journal
- Accession number :
- 36748821
- Full Text :
- https://doi.org/10.1039/d2cp05793j