Matches in SemOpenAlex for { <https://semopenalex.org/work/W4313304463> ?p ?o ?g. }
Showing items 1 to 73 of
73
with 100 items per page.
- W4313304463 abstract "We propose characteristics-informed neural networks (CINN), a simple and efficient machine learning approach for solving forward and inverse problems involving hyperbolic PDEs. Like physics-informed neural networks (PINN), CINN is a meshless machine learning solver with universal approximation capabilities. Unlike PINN, which enforces a PDE softly via a multi-part loss function, CINN encodes the characteristics of the PDE in a general-purpose deep neural network by adding a characteristic layer. This neural network is trained with the usual MSE data-fitting regression loss and does not require residual losses on collocation points. This leads to faster training and can avoid well-known pathologies of gradient descent optimization of multi-part PINN loss functions. This paper focuses on linear transport phenomena, in which case it is shown that, if the characteristic ODEs can be solved exactly, then the output of a CINN is an exact solution of the PDE, even at initialization, preventing the occurrence of non-physical solutions. In addition, a CINN can also be trained with soft penalty constraints that enforce, for example, periodic or Neumman boundary conditions, without losing the property that the output satisfies the PDE automatically. We also propose an architecture that extends the CINN approach to linear hyperbolic systems of PDEs. All CINN architectures proposed here can be trained end-to-end from sample data using standard deep learning software. Experiments with the simple advection equation, a stiff periodic advection equation, and an acoustics problem where data from one field is used to predict the other, unseen field, indicate that CINN is able to improve on the accuracy of the baseline PINN, in some cases by a considerable margin, while also being significantly faster to train and avoiding non-physical solutions. An extension to nonlinear PDEs is also briefly discussed." @default.
- W4313304463 created "2023-01-06" @default.
- W4313304463 creator A5026990034 @default.
- W4313304463 date "2022-12-28" @default.
- W4313304463 modified "2023-09-30" @default.
- W4313304463 title "Characteristics-Informed Neural Networks for Forward and Inverse Hyperbolic Problems" @default.
- W4313304463 doi "https://doi.org/10.48550/arxiv.2212.14012" @default.
- W4313304463 hasPublicationYear "2022" @default.
- W4313304463 type Work @default.
- W4313304463 citedByCount "0" @default.
- W4313304463 crossrefType "posted-content" @default.
- W4313304463 hasAuthorship W4313304463A5026990034 @default.
- W4313304463 hasBestOaLocation W43133044631 @default.
- W4313304463 hasConcept C111472728 @default.
- W4313304463 hasConcept C114466953 @default.
- W4313304463 hasConcept C119857082 @default.
- W4313304463 hasConcept C126255220 @default.
- W4313304463 hasConcept C134306372 @default.
- W4313304463 hasConcept C135252773 @default.
- W4313304463 hasConcept C138885662 @default.
- W4313304463 hasConcept C153258448 @default.
- W4313304463 hasConcept C154945302 @default.
- W4313304463 hasConcept C155032097 @default.
- W4313304463 hasConcept C199360897 @default.
- W4313304463 hasConcept C207467116 @default.
- W4313304463 hasConcept C2524010 @default.
- W4313304463 hasConcept C2778770139 @default.
- W4313304463 hasConcept C2780586882 @default.
- W4313304463 hasConcept C28826006 @default.
- W4313304463 hasConcept C33923547 @default.
- W4313304463 hasConcept C34862557 @default.
- W4313304463 hasConcept C41008148 @default.
- W4313304463 hasConcept C50644808 @default.
- W4313304463 hasConcept C80023036 @default.
- W4313304463 hasConcept C92047909 @default.
- W4313304463 hasConceptScore W4313304463C111472728 @default.
- W4313304463 hasConceptScore W4313304463C114466953 @default.
- W4313304463 hasConceptScore W4313304463C119857082 @default.
- W4313304463 hasConceptScore W4313304463C126255220 @default.
- W4313304463 hasConceptScore W4313304463C134306372 @default.
- W4313304463 hasConceptScore W4313304463C135252773 @default.
- W4313304463 hasConceptScore W4313304463C138885662 @default.
- W4313304463 hasConceptScore W4313304463C153258448 @default.
- W4313304463 hasConceptScore W4313304463C154945302 @default.
- W4313304463 hasConceptScore W4313304463C155032097 @default.
- W4313304463 hasConceptScore W4313304463C199360897 @default.
- W4313304463 hasConceptScore W4313304463C207467116 @default.
- W4313304463 hasConceptScore W4313304463C2524010 @default.
- W4313304463 hasConceptScore W4313304463C2778770139 @default.
- W4313304463 hasConceptScore W4313304463C2780586882 @default.
- W4313304463 hasConceptScore W4313304463C28826006 @default.
- W4313304463 hasConceptScore W4313304463C33923547 @default.
- W4313304463 hasConceptScore W4313304463C34862557 @default.
- W4313304463 hasConceptScore W4313304463C41008148 @default.
- W4313304463 hasConceptScore W4313304463C50644808 @default.
- W4313304463 hasConceptScore W4313304463C80023036 @default.
- W4313304463 hasConceptScore W4313304463C92047909 @default.
- W4313304463 hasLocation W43133044631 @default.
- W4313304463 hasOpenAccess W4313304463 @default.
- W4313304463 hasPrimaryLocation W43133044631 @default.
- W4313304463 hasRelatedWork W2046055439 @default.
- W4313304463 hasRelatedWork W2140414732 @default.
- W4313304463 hasRelatedWork W2337850389 @default.
- W4313304463 hasRelatedWork W2978031686 @default.
- W4313304463 hasRelatedWork W3046740966 @default.
- W4313304463 hasRelatedWork W3123071383 @default.
- W4313304463 hasRelatedWork W3155831151 @default.
- W4313304463 hasRelatedWork W3159389381 @default.
- W4313304463 hasRelatedWork W3217213740 @default.
- W4313304463 hasRelatedWork W4220847609 @default.
- W4313304463 isParatext "false" @default.
- W4313304463 isRetracted "false" @default.
- W4313304463 workType "article" @default.