FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3178836698> ?p ?o ?g. }

• W3178836698 abstract "Advances in differentiable numerical integrators have enabled the use of gradient descent techniques to learn ordinary differential equations (ODEs). In the context of machine learning, differentiable solvers are central for Neural ODEs (NODEs), a class of deep learning models with continuous depth, rather than discrete layers. However, these integrators can be unsatisfactorily slow and inaccurate when learning systems of ODEs from long sequences, or when solutions of the system vary at widely different timescales in each dimension. In this paper we propose an alternative approach to learning ODEs from data: we represent the underlying ODE as a vector field that is related to another base vector field by a differentiable bijection, modelled by an invertible neural network. By restricting the base ODE to be amenable to integration, we can drastically speed up and improve the robustness of integration. We demonstrate the efficacy of our method in training and evaluating continuous neural networks models, as well as in learning benchmark ODE systems. We observe improvements of up to two orders of magnitude when integrating learned ODEs with GPUs computation." @default.
• W3178836698 created "2021-07-19" @default.
• W3178836698 creator A5016732447 @default.
• W3178836698 creator A5023657363 @default.
• W3178836698 creator A5033725695 @default.
• W3178836698 creator A5062619542 @default.
• W3178836698 creator A5077799676 @default.
• W3178836698 date "2021-07-04" @default.
• W3178836698 modified "2023-09-27" @default.
• W3178836698 title "Learning ODEs via Diffeomorphisms for Fast and Robust Integration." @default.
• W3178836698 cites W1557324374 @default.
• W3178836698 cites W1567995217 @default.
• W3178836698 cites W2008007187 @default.
• W3178836698 cites W2011301426 @default.
• W3178836698 cites W2024494042 @default.
• W3178836698 cites W2129202194 @default.
• W3178836698 cites W2587284713 @default.
• W3178836698 cites W2605147767 @default.
• W3178836698 cites W2610857016 @default.
• W3178836698 cites W2887540873 @default.
• W3178836698 cites W2930930439 @default.
• W3178836698 cites W2958796454 @default.
• W3178836698 cites W2962695743 @default.
• W3178836698 cites W2963090522 @default.
• W3178836698 cites W2963641970 @default.
• W3178836698 cites W2963755523 @default.
• W3178836698 cites W2965543245 @default.
• W3178836698 cites W2970181183 @default.
• W3178836698 cites W2970535233 @default.
• W3178836698 cites W2970700221 @default.
• W3178836698 cites W2970898247 @default.
• W3178836698 cites W2970971581 @default.
• W3178836698 cites W3016115703 @default.
• W3178836698 cites W3021268132 @default.
• W3178836698 cites W3034786252 @default.
• W3178836698 cites W3094623068 @default.
• W3178836698 cites W3096986660 @default.
• W3178836698 cites W3099254792 @default.
• W3178836698 cites W3099878876 @default.
• W3178836698 cites W3100844775 @default.
• W3178836698 cites W3102812543 @default.
• W3178836698 cites W3104380914 @default.
• W3178836698 cites W3105200108 @default.
• W3178836698 cites W3105999403 @default.
• W3178836698 cites W3120128856 @default.
• W3178836698 cites W3150807214 @default.
• W3178836698 cites W3206777520 @default.
• W3178836698 cites W88520345 @default.
• W3178836698 cites W9124626 @default.
• W3178836698 hasPublicationYear "2021" @default.
• W3178836698 type Work @default.
• W3178836698 sameAs 3178836698 @default.
• W3178836698 citedByCount "0" @default.
• W3178836698 crossrefType "posted-content" @default.
• W3178836698 hasAuthorship W3178836698A5016732447 @default.
• W3178836698 hasAuthorship W3178836698A5023657363 @default.
• W3178836698 hasAuthorship W3178836698A5033725695 @default.
• W3178836698 hasAuthorship W3178836698A5062619542 @default.
• W3178836698 hasAuthorship W3178836698A5077799676 @default.
• W3178836698 hasConcept C104317684 @default.
• W3178836698 hasConcept C114466953 @default.
• W3178836698 hasConcept C134306372 @default.
• W3178836698 hasConcept C151730666 @default.
• W3178836698 hasConcept C154945302 @default.
• W3178836698 hasConcept C185592680 @default.
• W3178836698 hasConcept C199360897 @default.
• W3178836698 hasConcept C202615002 @default.
• W3178836698 hasConcept C2779343474 @default.
• W3178836698 hasConcept C28826006 @default.
• W3178836698 hasConcept C33923547 @default.
• W3178836698 hasConcept C34862557 @default.
• W3178836698 hasConcept C41008148 @default.
• W3178836698 hasConcept C50644808 @default.
• W3178836698 hasConcept C51544822 @default.
• W3178836698 hasConcept C55493867 @default.
• W3178836698 hasConcept C63479239 @default.
• W3178836698 hasConcept C78045399 @default.
• W3178836698 hasConcept C86803240 @default.
• W3178836698 hasConceptScore W3178836698C104317684 @default.
• W3178836698 hasConceptScore W3178836698C114466953 @default.
• W3178836698 hasConceptScore W3178836698C134306372 @default.
• W3178836698 hasConceptScore W3178836698C151730666 @default.
• W3178836698 hasConceptScore W3178836698C154945302 @default.
• W3178836698 hasConceptScore W3178836698C185592680 @default.
• W3178836698 hasConceptScore W3178836698C199360897 @default.
• W3178836698 hasConceptScore W3178836698C202615002 @default.
• W3178836698 hasConceptScore W3178836698C2779343474 @default.
• W3178836698 hasConceptScore W3178836698C28826006 @default.
• W3178836698 hasConceptScore W3178836698C33923547 @default.
• W3178836698 hasConceptScore W3178836698C34862557 @default.
• W3178836698 hasConceptScore W3178836698C41008148 @default.
• W3178836698 hasConceptScore W3178836698C50644808 @default.
• W3178836698 hasConceptScore W3178836698C51544822 @default.
• W3178836698 hasConceptScore W3178836698C55493867 @default.
• W3178836698 hasConceptScore W3178836698C63479239 @default.
• W3178836698 hasConceptScore W3178836698C78045399 @default.
• W3178836698 hasConceptScore W3178836698C86803240 @default.
• W3178836698 hasLocation W31788366981 @default.
• W3178836698 hasOpenAccess W3178836698 @default.
• W3178836698 hasPrimaryLocation W31788366981 @default.

• next