Matches in SemOpenAlex for { <https://semopenalex.org/work/W4200634757> ?p ?o ?g. }
Showing items 1 to 97 of
97
with 100 items per page.
- W4200634757 abstract "While deep learning algorithms demonstrate a great potential in scientific computing, its application to multi-scale problems remains to be a big challenge. This is manifested by the frequency principle that neural networks tend to learn low frequency components first. Novel architectures such as multi-scale deep neural network (MscaleDNN) were proposed to alleviate this problem to some extent. In this paper, we construct a subspace decomposition based DNN (dubbed SD$^2$NN) architecture for a class of multi-scale problems by combining traditional numerical analysis ideas and MscaleDNN algorithms. The proposed architecture includes one low frequency normal DNN submodule, and one (or a few) high frequency MscaleDNN submodule(s), which are designed to capture the smooth part and the oscillatory part of the multi-scale solutions, respectively. In addition, a novel trigonometric activation function is incorporated in the SD$^2$NN model. We demonstrate the performance of the SD$^2$NN architecture through several benchmark multi-scale problems in regular or irregular geometric domains. Numerical results show that the SD$^2$NN model is superior to existing models such as MscaleDNN." @default.
- W4200634757 created "2021-12-31" @default.
- W4200634757 creator A5002236438 @default.
- W4200634757 creator A5029602836 @default.
- W4200634757 creator A5080798381 @default.
- W4200634757 date "2022-01-01" @default.
- W4200634757 modified "2023-10-17" @default.
- W4200634757 title "Subspace Decomposition Based Dnn Algorithm for Elliptic-Type Multi-Scale Pdes" @default.
- W4200634757 cites W1856502440 @default.
- W4200634757 cites W1969046853 @default.
- W4200634757 cites W1978691912 @default.
- W4200634757 cites W1980404981 @default.
- W4200634757 cites W1990157709 @default.
- W4200634757 cites W2017085690 @default.
- W4200634757 cites W2027748639 @default.
- W4200634757 cites W2029918260 @default.
- W4200634757 cites W2078045751 @default.
- W4200634757 cites W2126028850 @default.
- W4200634757 cites W2134350470 @default.
- W4200634757 cites W2153357396 @default.
- W4200634757 cites W2154122281 @default.
- W4200634757 cites W2157935711 @default.
- W4200634757 cites W2163242768 @default.
- W4200634757 cites W2507348356 @default.
- W4200634757 cites W2600297185 @default.
- W4200634757 cites W2625995436 @default.
- W4200634757 cites W2749028154 @default.
- W4200634757 cites W2760972773 @default.
- W4200634757 cites W2887569307 @default.
- W4200634757 cites W2899283552 @default.
- W4200634757 cites W2919115771 @default.
- W4200634757 cites W2948551291 @default.
- W4200634757 cites W2962846611 @default.
- W4200634757 cites W2963634130 @default.
- W4200634757 cites W2964110066 @default.
- W4200634757 cites W2984061542 @default.
- W4200634757 cites W3045146186 @default.
- W4200634757 cites W3088681382 @default.
- W4200634757 cites W3093990252 @default.
- W4200634757 cites W3100666994 @default.
- W4200634757 cites W3101985406 @default.
- W4200634757 cites W3103355665 @default.
- W4200634757 cites W3105606612 @default.
- W4200634757 cites W3116268267 @default.
- W4200634757 cites W3137368077 @default.
- W4200634757 cites W4292403327 @default.
- W4200634757 doi "https://doi.org/10.2139/ssrn.4020731" @default.
- W4200634757 hasPublicationYear "2022" @default.
- W4200634757 type Work @default.
- W4200634757 citedByCount "1" @default.
- W4200634757 countsByYear W42006347572022 @default.
- W4200634757 crossrefType "journal-article" @default.
- W4200634757 hasAuthorship W4200634757A5002236438 @default.
- W4200634757 hasAuthorship W4200634757A5029602836 @default.
- W4200634757 hasAuthorship W4200634757A5080798381 @default.
- W4200634757 hasBestOaLocation W42006347572 @default.
- W4200634757 hasConcept C11413529 @default.
- W4200634757 hasConcept C121332964 @default.
- W4200634757 hasConcept C124681953 @default.
- W4200634757 hasConcept C154945302 @default.
- W4200634757 hasConcept C18903297 @default.
- W4200634757 hasConcept C2777299769 @default.
- W4200634757 hasConcept C2778755073 @default.
- W4200634757 hasConcept C32834561 @default.
- W4200634757 hasConcept C33923547 @default.
- W4200634757 hasConcept C41008148 @default.
- W4200634757 hasConcept C62520636 @default.
- W4200634757 hasConcept C86803240 @default.
- W4200634757 hasConceptScore W4200634757C11413529 @default.
- W4200634757 hasConceptScore W4200634757C121332964 @default.
- W4200634757 hasConceptScore W4200634757C124681953 @default.
- W4200634757 hasConceptScore W4200634757C154945302 @default.
- W4200634757 hasConceptScore W4200634757C18903297 @default.
- W4200634757 hasConceptScore W4200634757C2777299769 @default.
- W4200634757 hasConceptScore W4200634757C2778755073 @default.
- W4200634757 hasConceptScore W4200634757C32834561 @default.
- W4200634757 hasConceptScore W4200634757C33923547 @default.
- W4200634757 hasConceptScore W4200634757C41008148 @default.
- W4200634757 hasConceptScore W4200634757C62520636 @default.
- W4200634757 hasConceptScore W4200634757C86803240 @default.
- W4200634757 hasLocation W42006347571 @default.
- W4200634757 hasLocation W42006347572 @default.
- W4200634757 hasOpenAccess W4200634757 @default.
- W4200634757 hasPrimaryLocation W42006347571 @default.
- W4200634757 hasRelatedWork W2090558690 @default.
- W4200634757 hasRelatedWork W2105880240 @default.
- W4200634757 hasRelatedWork W2123357356 @default.
- W4200634757 hasRelatedWork W2349865494 @default.
- W4200634757 hasRelatedWork W2372553222 @default.
- W4200634757 hasRelatedWork W2592326642 @default.
- W4200634757 hasRelatedWork W3101673024 @default.
- W4200634757 hasRelatedWork W3102072267 @default.
- W4200634757 hasRelatedWork W3157195516 @default.
- W4200634757 hasRelatedWork W3157620392 @default.
- W4200634757 isParatext "false" @default.
- W4200634757 isRetracted "false" @default.
- W4200634757 workType "article" @default.