Published September 17, 2021
| Version v1
Dataset
Open
Sensitivity benchmarks of structural representations for atomic-scale machine learning
Creators
- 1. Laboratory of Computational Science and Modelling, Institute of Materials, Ecole Polytechnique Federale de Lausanne, Lausanne 1015, Switzerland
* Contact person
Description
This dataset contains three sets of CH4 geometries that are distorted along special directions, to reveal the sensitivity to atomic displacements of structural descriptors used in machine-learning applications. The structures are stored in a format that can be visualized on http://chemiscope.org, and contain also DFT-computed energies, as well as the sensitivity analysis of four different kinds of features.
Files
File preview
files_description.md
All files
Files
(163.7 KiB)
| Name | Apps | Size | |
|---|---|---|---|
|
md5:4628ef19c07eedf13eaccf0deed64f3f
|
384 Bytes | Preview Download | |
|
md5:92e76339ffd8b20ef12d634475910a4e
|
|
62.5 KiB | Download |
|
md5:d5bfbe6afd3133945498006f1830cb00
|
|
58.1 KiB | Download |
|
md5:42ac35280baa1bac75249d65577e966b
|
1.5 KiB | Preview Download | |
|
md5:df08fd38bd82b76ab2349ffe78f70c9a
|
|
41.3 KiB | Download |
References
Preprint Sergey N. Pozdnyakov, Liwei Zhang, Christoph Ortner, Gabor Csanyi, and Michele Ceriotti, Open Research Europe (submission in preparation)