FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3131416917> ?p ?o ?g. }

• W3131416917 abstract "Recent work has shown deep learning can accelerate the prediction of physical dynamics relative to numerical solvers. However, limited physical accuracy and an inability to generalize under distributional shift limit its applicability to the real world. We propose to improve accuracy and generalization by incorporating symmetries into convolutional neural networks. Specifically, we employ a variety of methods each tailored to enforce a different symmetry. Our models are both theoretically and experimentally robust to distributional shift by symmetry group transformations and enjoy favorable sample complexity. We demonstrate the advantage of our approach on a variety of physical dynamics including Rayleigh–Benard convection and real-world ocean currents and temperatures. Compare with image or text applications, our work is a significant step towards applying equivariant neural networks to high-dimensional systems with complex dynamics." @default.
• W3131416917 created "2021-03-01" @default.
• W3131416917 creator A5009851374 @default.
• W3131416917 creator A5020217201 @default.
• W3131416917 creator A5057778679 @default.
• W3131416917 date "2021-05-03" @default.
• W3131416917 modified "2023-09-23" @default.
• W3131416917 title "Incorporating Symmetry into Deep Dynamics Models for Improved Generalization" @default.
• W3131416917 cites W1576838367 @default.
• W3131416917 cites W1901129140 @default.
• W3131416917 cites W1912570122 @default.
• W3131416917 cites W2029030701 @default.
• W3131416917 cites W2033811429 @default.
• W3131416917 cites W2053453946 @default.
• W3131416917 cites W2161728228 @default.
• W3131416917 cites W2259303769 @default.
• W3131416917 cites W2279221249 @default.
• W3131416917 cites W2501995758 @default.
• W3131416917 cites W2576915720 @default.
• W3131416917 cites W2769152880 @default.
• W3131416917 cites W2772097715 @default.
• W3131416917 cites W2806209507 @default.
• W3131416917 cites W2899283552 @default.
• W3131416917 cites W2902894539 @default.
• W3131416917 cites W2919774339 @default.
• W3131416917 cites W2936357167 @default.
• W3131416917 cites W2946794331 @default.
• W3131416917 cites W2948563793 @default.
• W3131416917 cites W2949650786 @default.
• W3131416917 cites W2951651290 @default.
• W3131416917 cites W2962748579 @default.
• W3131416917 cites W2963125871 @default.
• W3131416917 cites W2963402657 @default.
• W3131416917 cites W2963504932 @default.
• W3131416917 cites W2963755523 @default.
• W3131416917 cites W2963887375 @default.
• W3131416917 cites W2963926704 @default.
• W3131416917 cites W2963942037 @default.
• W3131416917 cites W2964270168 @default.
• W3131416917 cites W2970612144 @default.
• W3131416917 cites W2970661753 @default.
• W3131416917 cites W2970754912 @default.
• W3131416917 cites W2970756352 @default.
• W3131416917 cites W2971940059 @default.
• W3131416917 cites W2995360807 @default.
• W3131416917 cites W2996406751 @default.
• W3131416917 cites W2998503299 @default.
• W3131416917 cites W3008803199 @default.
• W3131416917 cites W3015879326 @default.
• W3131416917 cites W3080930191 @default.
• W3131416917 cites W3143460965 @default.
• W3131416917 cites W2886835484 @default.
• W3131416917 cites W2963459876 @default.
• W3131416917 hasPublicationYear "2021" @default.
• W3131416917 type Work @default.
• W3131416917 sameAs 3131416917 @default.
• W3131416917 citedByCount "6" @default.
• W3131416917 countsByYear W31314169172021 @default.
• W3131416917 crossrefType "proceedings-article" @default.
• W3131416917 hasAuthorship W3131416917A5009851374 @default.
• W3131416917 hasAuthorship W3131416917A5020217201 @default.
• W3131416917 hasAuthorship W3131416917A5057778679 @default.
• W3131416917 hasConcept C108583219 @default.
• W3131416917 hasConcept C121332964 @default.
• W3131416917 hasConcept C121864883 @default.
• W3131416917 hasConcept C134306372 @default.
• W3131416917 hasConcept C136197465 @default.
• W3131416917 hasConcept C151201525 @default.
• W3131416917 hasConcept C154945302 @default.
• W3131416917 hasConcept C171036898 @default.
• W3131416917 hasConcept C177148314 @default.
• W3131416917 hasConcept C202444582 @default.
• W3131416917 hasConcept C2524010 @default.
• W3131416917 hasConcept C2779886137 @default.
• W3131416917 hasConcept C33923547 @default.
• W3131416917 hasConcept C41008148 @default.
• W3131416917 hasConcept C50644808 @default.
• W3131416917 hasConcept C81363708 @default.
• W3131416917 hasConcept C96469262 @default.
• W3131416917 hasConceptScore W3131416917C108583219 @default.
• W3131416917 hasConceptScore W3131416917C121332964 @default.
• W3131416917 hasConceptScore W3131416917C121864883 @default.
• W3131416917 hasConceptScore W3131416917C134306372 @default.
• W3131416917 hasConceptScore W3131416917C136197465 @default.
• W3131416917 hasConceptScore W3131416917C151201525 @default.
• W3131416917 hasConceptScore W3131416917C154945302 @default.
• W3131416917 hasConceptScore W3131416917C171036898 @default.
• W3131416917 hasConceptScore W3131416917C177148314 @default.
• W3131416917 hasConceptScore W3131416917C202444582 @default.
• W3131416917 hasConceptScore W3131416917C2524010 @default.
• W3131416917 hasConceptScore W3131416917C2779886137 @default.
• W3131416917 hasConceptScore W3131416917C33923547 @default.
• W3131416917 hasConceptScore W3131416917C41008148 @default.
• W3131416917 hasConceptScore W3131416917C50644808 @default.
• W3131416917 hasConceptScore W3131416917C81363708 @default.
• W3131416917 hasConceptScore W3131416917C96469262 @default.
• W3131416917 hasOpenAccess W3131416917 @default.
• W3131416917 hasRelatedWork W2212676342 @default.
• W3131416917 hasRelatedWork W2741072286 @default.
• W3131416917 hasRelatedWork W2918988876 @default.

• next