<?xml version='1.0' encoding='utf-8'?> <oai_dc:dc xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:oai_dc="http://www.openarchives.org/OAI/2.0/oai_dc/" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://www.openarchives.org/OAI/2.0/oai_dc/ http://www.openarchives.org/OAI/2.0/oai_dc.xsd"> <dc:creator>Pozdnyakov, Sergey</dc:creator> <dc:creator>Ceriotti, Michele</dc:creator> <dc:date>2021-09-17</dc:date> <dc: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.</dc:description> <dc:identifier>https://archive.materialscloud.org/record/2021.149</dc:identifier> <dc:identifier>doi:10.24435/materialscloud:7z-g6</dc:identifier> <dc:identifier>mcid:2021.149</dc:identifier> <dc:identifier>oai:materialscloud.org:1024</dc:identifier> <dc:language>en</dc:language> <dc:publisher>Materials Cloud</dc:publisher> <dc:rights>info:eu-repo/semantics/openAccess</dc:rights> <dc:rights>Creative Commons Attribution Non Commercial 4.0 International https://creativecommons.org/licenses/by-nc/4.0/legalcode</dc:rights> <dc:subject>DFT</dc:subject> <dc:subject>methane</dc:subject> <dc:subject>sensitivity</dc:subject> <dc:subject>representations</dc:subject> <dc:subject>machine learning</dc:subject> <dc:subject>MARVEL</dc:subject> <dc:subject>SNSF</dc:subject> <dc:subject>ERC</dc:subject> <dc:title>Sensitivity benchmarks of structural representations for atomic-scale machine learning</dc:title> <dc:type>Dataset</dc:type> </oai_dc:dc>