Matches in SemOpenAlex for { <https://semopenalex.org/work/W4287671531> ?p ?o ?g. }
Showing items 1 to 75 of
75
with 100 items per page.
- W4287671531 abstract "Eficient, physically-inspired descriptors of the structure and composition of molecules and materials play a key role in the application of machine-learning techniques to atomistic simulations. The proliferation of approaches, as well as the fact that each choice of features can lead to very different behavior depending on how they are used, e.g. by introducing non-linear kernels and non-Euclidean metrics to manipulate them, makes it difficult to objectively compare different methods, and to address fundamental questions on how one feature space is related to another. In this work we introduce a framework to compare different sets of descriptors, and different ways of transforming them by means of metrics and kernels, in terms of the structure of the feature space that they induce. We define diagnostic tools to determine whether alternative feature spaces contain equivalent amounts of information, and whether the common information is substantially distorted when going from one feature space to another. We compare, in particular, representations that are built in terms of n-body correlations of the atom density, quantitatively assessing the information loss associated with the use of low-order features. We also investigate the impact of different choices of basis functions and hyperparameters of the widely used SOAP and Behler-Parrinello features, and investigate how the use of non-linear kernels, and of a Wasserstein-type metric, change the structure of the feature space in comparison to a simpler linear feature space." @default.
- W4287671531 created "2022-07-25" @default.
- W4287671531 creator A5015199441 @default.
- W4287671531 creator A5021241296 @default.
- W4287671531 creator A5030473273 @default.
- W4287671531 creator A5087882510 @default.
- W4287671531 date "2020-09-06" @default.
- W4287671531 modified "2023-09-29" @default.
- W4287671531 title "The role of feature space in atomistic learning" @default.
- W4287671531 doi "https://doi.org/10.48550/arxiv.2009.02741" @default.
- W4287671531 hasPublicationYear "2020" @default.
- W4287671531 type Work @default.
- W4287671531 citedByCount "0" @default.
- W4287671531 crossrefType "posted-content" @default.
- W4287671531 hasAuthorship W4287671531A5015199441 @default.
- W4287671531 hasAuthorship W4287671531A5021241296 @default.
- W4287671531 hasAuthorship W4287671531A5030473273 @default.
- W4287671531 hasAuthorship W4287671531A5087882510 @default.
- W4287671531 hasBestOaLocation W42876715311 @default.
- W4287671531 hasConcept C111919701 @default.
- W4287671531 hasConcept C119857082 @default.
- W4287671531 hasConcept C124101348 @default.
- W4287671531 hasConcept C12426560 @default.
- W4287671531 hasConcept C127413603 @default.
- W4287671531 hasConcept C138885662 @default.
- W4287671531 hasConcept C153180895 @default.
- W4287671531 hasConcept C154945302 @default.
- W4287671531 hasConcept C176217482 @default.
- W4287671531 hasConcept C186450821 @default.
- W4287671531 hasConcept C202444582 @default.
- W4287671531 hasConcept C21547014 @default.
- W4287671531 hasConcept C2524010 @default.
- W4287671531 hasConcept C2776401178 @default.
- W4287671531 hasConcept C2778572836 @default.
- W4287671531 hasConcept C33923547 @default.
- W4287671531 hasConcept C41008148 @default.
- W4287671531 hasConcept C41895202 @default.
- W4287671531 hasConcept C80444323 @default.
- W4287671531 hasConcept C83665646 @default.
- W4287671531 hasConceptScore W4287671531C111919701 @default.
- W4287671531 hasConceptScore W4287671531C119857082 @default.
- W4287671531 hasConceptScore W4287671531C124101348 @default.
- W4287671531 hasConceptScore W4287671531C12426560 @default.
- W4287671531 hasConceptScore W4287671531C127413603 @default.
- W4287671531 hasConceptScore W4287671531C138885662 @default.
- W4287671531 hasConceptScore W4287671531C153180895 @default.
- W4287671531 hasConceptScore W4287671531C154945302 @default.
- W4287671531 hasConceptScore W4287671531C176217482 @default.
- W4287671531 hasConceptScore W4287671531C186450821 @default.
- W4287671531 hasConceptScore W4287671531C202444582 @default.
- W4287671531 hasConceptScore W4287671531C21547014 @default.
- W4287671531 hasConceptScore W4287671531C2524010 @default.
- W4287671531 hasConceptScore W4287671531C2776401178 @default.
- W4287671531 hasConceptScore W4287671531C2778572836 @default.
- W4287671531 hasConceptScore W4287671531C33923547 @default.
- W4287671531 hasConceptScore W4287671531C41008148 @default.
- W4287671531 hasConceptScore W4287671531C41895202 @default.
- W4287671531 hasConceptScore W4287671531C80444323 @default.
- W4287671531 hasConceptScore W4287671531C83665646 @default.
- W4287671531 hasLocation W42876715311 @default.
- W4287671531 hasOpenAccess W4287671531 @default.
- W4287671531 hasPrimaryLocation W42876715311 @default.
- W4287671531 hasRelatedWork W10121358 @default.
- W4287671531 hasRelatedWork W10975483 @default.
- W4287671531 hasRelatedWork W11478586 @default.
- W4287671531 hasRelatedWork W11765363 @default.
- W4287671531 hasRelatedWork W43565 @default.
- W4287671531 hasRelatedWork W5374421 @default.
- W4287671531 hasRelatedWork W5646511 @default.
- W4287671531 hasRelatedWork W5687595 @default.
- W4287671531 hasRelatedWork W5738750 @default.
- W4287671531 hasRelatedWork W8815205 @default.
- W4287671531 isParatext "false" @default.
- W4287671531 isRetracted "false" @default.
- W4287671531 workType "article" @default.