Complete and Efficient Covariants for Three-Dimensional Point Configurations with Application to Learning Molecular Quantum Properties
Hartmut Maennel, Oliver T Unke, Klaus-Robert Müller · 2024
Read Complete and Efficient Covariants for Three-Dimensional Point Configurations with Application to Learning Molecular Quantum Properties by Hartmut Maennel, Oliver T Unke, Klaus-Robert Müller (2024) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-11684023.txt.
Description
Hartmut Maennel, Oliver Unke and Klaus-Robert Müller wrote a 2024 paper on learning molecule traits with machine learning. A good model should respect how molecules turn in space. Low-order features that do this are known to be incomplete. The team set out to prove what higher-order features can do.
They prove broad claims about when such feature sets are complete. For a molecule with a set number of atoms, they give a count of features that is enough. They also swap a common step for plain matrix work, which cuts the cost a lot. The method fits quantum chemistry, and any task with points in space.
Catalog record
| CREATOR | Hartmut Maennel, Oliver T Unke, Klaus-Robert Müller |
|---|---|
| YEAR | 2024 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 25 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |