Matches in SemOpenAlex for { <https://semopenalex.org/work/W3211537151> ?p ?o ?g. }
Showing items 1 to 78 of
78
with 100 items per page.
- W3211537151 abstract "Machine learning has enabled the prediction of quantum chemical properties with high accuracy and efficiency, allowing to bypass computationally costly ab initio calculations. Instead of training on a fixed set of properties, more recent approaches attempt to learn the electronic wavefunction (or density) as a central quantity of atomistic systems, from which all other observables can be derived. This is complicated by the fact that wavefunctions transform non-trivially under molecular rotations, which makes them a challenging prediction target. To solve this issue, we introduce general SE(3)-equivariant operations and building blocks for constructing deep learning architectures for geometric point cloud data and apply them to reconstruct wavefunctions of atomistic systems with unprecedented accuracy. Our model reduces prediction errors by up to two orders of magnitude compared to the previous state-of-the-art and makes it possible to derive properties such as energies and forces directly from the wavefunction in an end-to-end manner. We demonstrate the potential of our approach in a transfer learning application, where a model trained on low accuracy reference wavefunctions implicitly learns to correct for electronic many-body interactions from observables computed at a higher level of theory. Such machine-learned wavefunction surrogates pave the way towards novel semi-empirical methods, offering resolution at an electronic level while drastically decreasing computational cost. While we focus on physics applications in this contribution, the proposed equivariant framework for deep learning on point clouds is promising also beyond, say, in computer vision or graphics." @default.
- W3211537151 created "2021-11-22" @default.
- W3211537151 creator A5002843500 @default.
- W3211537151 creator A5011992388 @default.
- W3211537151 creator A5061366692 @default.
- W3211537151 creator A5062301881 @default.
- W3211537151 creator A5082698816 @default.
- W3211537151 creator A5087792082 @default.
- W3211537151 date "2021-12-06" @default.
- W3211537151 modified "2023-10-18" @default.
- W3211537151 title "SE(3)-equivariant prediction of molecular wavefunctions and electronic densities" @default.
- W3211537151 hasPublicationYear "2021" @default.
- W3211537151 type Work @default.
- W3211537151 sameAs 3211537151 @default.
- W3211537151 citedByCount "0" @default.
- W3211537151 crossrefType "proceedings-article" @default.
- W3211537151 hasAuthorship W3211537151A5002843500 @default.
- W3211537151 hasAuthorship W3211537151A5011992388 @default.
- W3211537151 hasAuthorship W3211537151A5061366692 @default.
- W3211537151 hasAuthorship W3211537151A5062301881 @default.
- W3211537151 hasAuthorship W3211537151A5082698816 @default.
- W3211537151 hasAuthorship W3211537151A5087792082 @default.
- W3211537151 hasConcept C108583219 @default.
- W3211537151 hasConcept C113603373 @default.
- W3211537151 hasConcept C11413529 @default.
- W3211537151 hasConcept C121332964 @default.
- W3211537151 hasConcept C121864883 @default.
- W3211537151 hasConcept C154945302 @default.
- W3211537151 hasConcept C171036898 @default.
- W3211537151 hasConcept C202444582 @default.
- W3211537151 hasConcept C32848918 @default.
- W3211537151 hasConcept C33923547 @default.
- W3211537151 hasConcept C41008148 @default.
- W3211537151 hasConcept C62520636 @default.
- W3211537151 hasConcept C80444323 @default.
- W3211537151 hasConcept C86025842 @default.
- W3211537151 hasConceptScore W3211537151C108583219 @default.
- W3211537151 hasConceptScore W3211537151C113603373 @default.
- W3211537151 hasConceptScore W3211537151C11413529 @default.
- W3211537151 hasConceptScore W3211537151C121332964 @default.
- W3211537151 hasConceptScore W3211537151C121864883 @default.
- W3211537151 hasConceptScore W3211537151C154945302 @default.
- W3211537151 hasConceptScore W3211537151C171036898 @default.
- W3211537151 hasConceptScore W3211537151C202444582 @default.
- W3211537151 hasConceptScore W3211537151C32848918 @default.
- W3211537151 hasConceptScore W3211537151C33923547 @default.
- W3211537151 hasConceptScore W3211537151C41008148 @default.
- W3211537151 hasConceptScore W3211537151C62520636 @default.
- W3211537151 hasConceptScore W3211537151C80444323 @default.
- W3211537151 hasConceptScore W3211537151C86025842 @default.
- W3211537151 hasLocation W32115371511 @default.
- W3211537151 hasOpenAccess W3211537151 @default.
- W3211537151 hasPrimaryLocation W32115371511 @default.
- W3211537151 hasRelatedWork W2170091541 @default.
- W3211537151 hasRelatedWork W2471434546 @default.
- W3211537151 hasRelatedWork W2515090858 @default.
- W3211537151 hasRelatedWork W2968406915 @default.
- W3211537151 hasRelatedWork W3010545730 @default.
- W3211537151 hasRelatedWork W3023537565 @default.
- W3211537151 hasRelatedWork W3023856540 @default.
- W3211537151 hasRelatedWork W3100344218 @default.
- W3211537151 hasRelatedWork W3100347995 @default.
- W3211537151 hasRelatedWork W3102579065 @default.
- W3211537151 hasRelatedWork W3104978323 @default.
- W3211537151 hasRelatedWork W3126613532 @default.
- W3211537151 hasRelatedWork W3127369373 @default.
- W3211537151 hasRelatedWork W3133901995 @default.
- W3211537151 hasRelatedWork W3134839668 @default.
- W3211537151 hasRelatedWork W3167942196 @default.
- W3211537151 hasRelatedWork W3194643087 @default.
- W3211537151 hasRelatedWork W3203740629 @default.
- W3211537151 hasRelatedWork W3204153538 @default.
- W3211537151 hasRelatedWork W633479708 @default.
- W3211537151 hasVolume "34" @default.
- W3211537151 isParatext "false" @default.
- W3211537151 isRetracted "false" @default.
- W3211537151 magId "3211537151" @default.
- W3211537151 workType "article" @default.