FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3205765690> ?p ?o ?g. }

• W3205765690 endingPage "114424" @default.
• W3205765690 startingPage "114424" @default.
• W3205765690 abstract "Physics-informed neural networks (PINNs) are increasingly employed to replace/augment traditional numerical methods in solving partial differential equations (PDEs). While state-of-the-art PINNs have many attractive features, they approximate a specific realization of a PDE system and hence are problem-specific. That is, the model needs to be re-trained each time the boundary conditions (BCs) and domain shape/size change. This limitation prohibits the application of PINNs to realistic or large-scale engineering problems especially since the costs and efforts associated with their training are considerable. We introduce a transferable framework for solving boundary value problems (BVPs) via deep neural networks which can be trained once and used forever for various unseen domains and BCs. We first introduce genomic flow network(GFNet), a neural network that can infer the solution of a BVP across arbitrary BCson a small square domain called genome. Then, we proposed mosaic flow(MF) predictor, a novel iterative algorithm that assembles the GFNet's inferences for BVPs on large domains with unseen sizes/shapes and BCs while preserving the spatial regularity of the solution. We demonstrate that our framework can estimate the solution of Laplace and Navier-Stokes equations in domains of unseen shapes and BCs that are, respectively, 1200 and 12 times larger than the training domains. Since our framework eliminates the need to re-train models for unseen domains and BCs, it demonstrates up to 3 orders-of-magnitude speedups compared to the state-of-the-art." @default.
• W3205765690 created "2021-10-25" @default.
• W3205765690 creator A5024791457 @default.
• W3205765690 creator A5062806994 @default.
• W3205765690 creator A5074121652 @default.
• W3205765690 creator A5078428103 @default.
• W3205765690 date "2022-02-01" @default.
• W3205765690 modified "2023-10-18" @default.
• W3205765690 title "Mosaic flows: A transferable deep learning framework for solving PDEs on unseen domains" @default.
• W3205765690 cites W1689711448 @default.
• W3205765690 cites W1901129140 @default.
• W3205765690 cites W1977046327 @default.
• W3205765690 cites W1984334096 @default.
• W3205765690 cites W1988115241 @default.
• W3205765690 cites W2004727054 @default.
• W3205765690 cites W2007347635 @default.
• W3205765690 cites W2017085690 @default.
• W3205765690 cites W2051434435 @default.
• W3205765690 cites W2060754775 @default.
• W3205765690 cites W2064675550 @default.
• W3205765690 cites W2139923370 @default.
• W3205765690 cites W2531409750 @default.
• W3205765690 cites W2534240011 @default.
• W3205765690 cites W2760972773 @default.
• W3205765690 cites W2770250658 @default.
• W3205765690 cites W2784733489 @default.
• W3205765690 cites W2864723431 @default.
• W3205765690 cites W2899283552 @default.
• W3205765690 cites W2919115771 @default.
• W3205765690 cites W2948230027 @default.
• W3205765690 cites W2948551291 @default.
• W3205765690 cites W2951392159 @default.
• W3205765690 cites W2961141911 @default.
• W3205765690 cites W2969381807 @default.
• W3205765690 cites W2974527409 @default.
• W3205765690 cites W2980396542 @default.
• W3205765690 cites W2987081155 @default.
• W3205765690 cites W2996028791 @default.
• W3205765690 cites W3003922491 @default.
• W3205765690 cites W3010839048 @default.
• W3205765690 cites W3028481880 @default.
• W3205765690 cites W3033800177 @default.
• W3205765690 cites W3037739398 @default.
• W3205765690 cites W3039204554 @default.
• W3205765690 cites W3041682155 @default.
• W3205765690 cites W3083791730 @default.
• W3205765690 cites W3093605970 @default.
• W3205765690 cites W3098546160 @default.
• W3205765690 cites W3100968477 @default.
• W3205765690 cites W3123883114 @default.
• W3205765690 cites W3135457600 @default.
• W3205765690 cites W3137474564 @default.
• W3205765690 cites W3141132194 @default.
• W3205765690 cites W3153200540 @default.
• W3205765690 doi "https://doi.org/10.1016/j.cma.2021.114424" @default.
• W3205765690 hasPublicationYear "2022" @default.
• W3205765690 type Work @default.
• W3205765690 sameAs 3205765690 @default.
• W3205765690 citedByCount "13" @default.
• W3205765690 countsByYear W32057656902021 @default.
• W3205765690 countsByYear W32057656902022 @default.
• W3205765690 countsByYear W32057656902023 @default.
• W3205765690 crossrefType "journal-article" @default.
• W3205765690 hasAuthorship W3205765690A5024791457 @default.
• W3205765690 hasAuthorship W3205765690A5062806994 @default.
• W3205765690 hasAuthorship W3205765690A5074121652 @default.
• W3205765690 hasAuthorship W3205765690A5078428103 @default.
• W3205765690 hasBestOaLocation W32057656901 @default.
• W3205765690 hasConcept C105795698 @default.
• W3205765690 hasConcept C108583219 @default.
• W3205765690 hasConcept C11413529 @default.
• W3205765690 hasConcept C126255220 @default.
• W3205765690 hasConcept C134306372 @default.
• W3205765690 hasConcept C138885662 @default.
• W3205765690 hasConcept C154945302 @default.
• W3205765690 hasConcept C182310444 @default.
• W3205765690 hasConcept C2524010 @default.
• W3205765690 hasConcept C2776401178 @default.
• W3205765690 hasConcept C2781089630 @default.
• W3205765690 hasConcept C28826006 @default.
• W3205765690 hasConcept C33923547 @default.
• W3205765690 hasConcept C36503486 @default.
• W3205765690 hasConcept C38349280 @default.
• W3205765690 hasConcept C41008148 @default.
• W3205765690 hasConcept C41895202 @default.
• W3205765690 hasConcept C50644808 @default.
• W3205765690 hasConcept C70615421 @default.
• W3205765690 hasConcept C80444323 @default.
• W3205765690 hasConcept C93779851 @default.
• W3205765690 hasConcept C97937538 @default.
• W3205765690 hasConceptScore W3205765690C105795698 @default.
• W3205765690 hasConceptScore W3205765690C108583219 @default.
• W3205765690 hasConceptScore W3205765690C11413529 @default.
• W3205765690 hasConceptScore W3205765690C126255220 @default.
• W3205765690 hasConceptScore W3205765690C134306372 @default.
• W3205765690 hasConceptScore W3205765690C138885662 @default.
• W3205765690 hasConceptScore W3205765690C154945302 @default.
• W3205765690 hasConceptScore W3205765690C182310444 @default.

• next