Matches in SemOpenAlex for { <https://semopenalex.org/work/W3167596497> ?p ?o ?g. }
Showing items 1 to 96 of
96
with 100 items per page.
- W3167596497 abstract "In this paper, a new Discontinuity Capturing Shallow Neural Network (DCSNN) for approximating $d$-dimensional piecewise continuous functions and for solving elliptic interface problems is developed. There are three novel features in the present network; namely, (i) jump discontinuities are accurately captured, (ii) it is completely shallow, comprising only one hidden layer, (iii) it is completely mesh-free for solving partial differential equations. The crucial idea here is that a $d$-dimensional piecewise continuous function can be extended to a continuous function defined in $(d+1)$-dimensional space, where the augmented coordinate variable labels the pieces of each sub-domain. We then construct a shallow neural network to express this new function. Since only one hidden layer is employed, the number of training parameters (weights and biases) scales linearly with the dimension and the neurons used in the hidden layer. For solving elliptic interface problems, the network is trained by minimizing the mean square error loss that consists of the residual of the governing equation, boundary condition, and the interface jump conditions. We perform a series of numerical tests to demonstrate the accuracy of the present network. Our DCSNN model is efficient due to only a moderate number of parameters needed to be trained (a few hundred parameters used throughout all numerical examples), and the results indicate good accuracy. Compared with the results obtained by the traditional grid-based immersed interface method (IIM), which is designed particularly for elliptic interface problems, our network model shows a better accuracy than IIM. We conclude by solving a six-dimensional problem to demonstrate the capability of the present network for high-dimensional applications." @default.
- W3167596497 created "2021-06-22" @default.
- W3167596497 creator A5023926770 @default.
- W3167596497 creator A5040103591 @default.
- W3167596497 creator A5049820569 @default.
- W3167596497 date "2021-06-10" @default.
- W3167596497 modified "2023-09-23" @default.
- W3167596497 title "A Discontinuity Capturing Shallow Neural Network for Elliptic Interface Problems" @default.
- W3167596497 cites W1490180844 @default.
- W3167596497 cites W1585773866 @default.
- W3167596497 cites W2007584322 @default.
- W3167596497 cites W2087070363 @default.
- W3167596497 cites W2103496339 @default.
- W3167596497 cites W2137983211 @default.
- W3167596497 cites W2749028154 @default.
- W3167596497 cites W2760972773 @default.
- W3167596497 cites W2766099245 @default.
- W3167596497 cites W2899283552 @default.
- W3167596497 cites W2908429425 @default.
- W3167596497 cites W2962727772 @default.
- W3167596497 cites W2963097630 @default.
- W3167596497 cites W2969390696 @default.
- W3167596497 cites W2985622559 @default.
- W3167596497 cites W3016115703 @default.
- W3167596497 cites W3016703299 @default.
- W3167596497 cites W3022977644 @default.
- W3167596497 cites W3146803896 @default.
- W3167596497 doi "https://doi.org/10.48550/arxiv.2106.05587" @default.
- W3167596497 hasPublicationYear "2021" @default.
- W3167596497 type Work @default.
- W3167596497 sameAs 3167596497 @default.
- W3167596497 citedByCount "2" @default.
- W3167596497 countsByYear W31675964972021 @default.
- W3167596497 crossrefType "posted-content" @default.
- W3167596497 hasAuthorship W3167596497A5023926770 @default.
- W3167596497 hasAuthorship W3167596497A5040103591 @default.
- W3167596497 hasAuthorship W3167596497A5049820569 @default.
- W3167596497 hasConcept C113843644 @default.
- W3167596497 hasConcept C11413529 @default.
- W3167596497 hasConcept C121332964 @default.
- W3167596497 hasConcept C129307140 @default.
- W3167596497 hasConcept C134306372 @default.
- W3167596497 hasConcept C14036430 @default.
- W3167596497 hasConcept C154945302 @default.
- W3167596497 hasConcept C155512373 @default.
- W3167596497 hasConcept C15627037 @default.
- W3167596497 hasConcept C157915830 @default.
- W3167596497 hasConcept C164660894 @default.
- W3167596497 hasConcept C17095337 @default.
- W3167596497 hasConcept C173608175 @default.
- W3167596497 hasConcept C2777042112 @default.
- W3167596497 hasConcept C2780695682 @default.
- W3167596497 hasConcept C33923547 @default.
- W3167596497 hasConcept C41008148 @default.
- W3167596497 hasConcept C50644808 @default.
- W3167596497 hasConcept C62520636 @default.
- W3167596497 hasConcept C78458016 @default.
- W3167596497 hasConcept C86803240 @default.
- W3167596497 hasConceptScore W3167596497C113843644 @default.
- W3167596497 hasConceptScore W3167596497C11413529 @default.
- W3167596497 hasConceptScore W3167596497C121332964 @default.
- W3167596497 hasConceptScore W3167596497C129307140 @default.
- W3167596497 hasConceptScore W3167596497C134306372 @default.
- W3167596497 hasConceptScore W3167596497C14036430 @default.
- W3167596497 hasConceptScore W3167596497C154945302 @default.
- W3167596497 hasConceptScore W3167596497C155512373 @default.
- W3167596497 hasConceptScore W3167596497C15627037 @default.
- W3167596497 hasConceptScore W3167596497C157915830 @default.
- W3167596497 hasConceptScore W3167596497C164660894 @default.
- W3167596497 hasConceptScore W3167596497C17095337 @default.
- W3167596497 hasConceptScore W3167596497C173608175 @default.
- W3167596497 hasConceptScore W3167596497C2777042112 @default.
- W3167596497 hasConceptScore W3167596497C2780695682 @default.
- W3167596497 hasConceptScore W3167596497C33923547 @default.
- W3167596497 hasConceptScore W3167596497C41008148 @default.
- W3167596497 hasConceptScore W3167596497C50644808 @default.
- W3167596497 hasConceptScore W3167596497C62520636 @default.
- W3167596497 hasConceptScore W3167596497C78458016 @default.
- W3167596497 hasConceptScore W3167596497C86803240 @default.
- W3167596497 hasLocation W31675964971 @default.
- W3167596497 hasOpenAccess W3167596497 @default.
- W3167596497 hasPrimaryLocation W31675964971 @default.
- W3167596497 hasRelatedWork W2002775473 @default.
- W3167596497 hasRelatedWork W2043634277 @default.
- W3167596497 hasRelatedWork W2065247516 @default.
- W3167596497 hasRelatedWork W2065680287 @default.
- W3167596497 hasRelatedWork W2070567053 @default.
- W3167596497 hasRelatedWork W2118767721 @default.
- W3167596497 hasRelatedWork W2494164944 @default.
- W3167596497 hasRelatedWork W3115996021 @default.
- W3167596497 hasRelatedWork W752408711 @default.
- W3167596497 hasRelatedWork W1734641249 @default.
- W3167596497 isParatext "false" @default.
- W3167596497 isRetracted "false" @default.
- W3167596497 magId "3167596497" @default.
- W3167596497 workType "article" @default.