Matches in SemOpenAlex for { <https://semopenalex.org/work/W3000403725> ?p ?o ?g. }
- W3000403725 endingPage "110444" @default.
- W3000403725 startingPage "110444" @default.
- W3000403725 abstract "The least squares method with deep neural networks as function parametrization has been applied to solve certain high-dimensional partial differential equations (PDEs) successfully; however, its convergence is slow and might not be guaranteed even within a simple class of PDEs. To improve the convergence of the network-based least squares model, we introduce a novel self-paced learning framework, SelectNet, which quantifies the difficulty of training samples, treats samples equally in the early stage of training, and slowly explores more challenging samples, e.g., samples with larger residual errors, mimicking the human cognitive process for more efficient learning. In particular, a selection network and the PDE solution network are trained simultaneously; the selection network adaptively weighting the training samples of the solution network achieving the goal of self-paced learning. Numerical examples indicate that the proposed SelectNet model outperforms existing models on the convergence speed and the convergence robustness, especially for low-regularity solutions." @default.
- W3000403725 created "2020-01-23" @default.
- W3000403725 creator A5000567490 @default.
- W3000403725 creator A5079204610 @default.
- W3000403725 creator A5079602544 @default.
- W3000403725 date "2021-09-01" @default.
- W3000403725 modified "2023-10-11" @default.
- W3000403725 title "SelectNet: Self-paced learning for high-dimensional partial differential equations" @default.
- W3000403725 cites W1970454553 @default.
- W3000403725 cites W1978075626 @default.
- W3000403725 cites W1978576933 @default.
- W3000403725 cites W2049002269 @default.
- W3000403725 cites W2103496339 @default.
- W3000403725 cites W2116514123 @default.
- W3000403725 cites W2137983211 @default.
- W3000403725 cites W2138917657 @default.
- W3000403725 cites W2148666448 @default.
- W3000403725 cites W2150323068 @default.
- W3000403725 cites W2152593035 @default.
- W3000403725 cites W2166116275 @default.
- W3000403725 cites W2528305538 @default.
- W3000403725 cites W2625995436 @default.
- W3000403725 cites W2749028154 @default.
- W3000403725 cites W2760972773 @default.
- W3000403725 cites W2770250658 @default.
- W3000403725 cites W2803629276 @default.
- W3000403725 cites W2885273747 @default.
- W3000403725 cites W2886881190 @default.
- W3000403725 cites W2899283552 @default.
- W3000403725 cites W2921935427 @default.
- W3000403725 cites W2963146412 @default.
- W3000403725 cites W2963172624 @default.
- W3000403725 cites W2964110066 @default.
- W3000403725 cites W2965192329 @default.
- W3000403725 cites W2992541290 @default.
- W3000403725 cites W2992906545 @default.
- W3000403725 cites W3031010353 @default.
- W3000403725 cites W3097724114 @default.
- W3000403725 cites W3099234608 @default.
- W3000403725 cites W3101260193 @default.
- W3000403725 cites W3210425550 @default.
- W3000403725 doi "https://doi.org/10.1016/j.jcp.2021.110444" @default.
- W3000403725 hasPublicationYear "2021" @default.
- W3000403725 type Work @default.
- W3000403725 sameAs 3000403725 @default.
- W3000403725 citedByCount "25" @default.
- W3000403725 countsByYear W30004037252020 @default.
- W3000403725 countsByYear W30004037252021 @default.
- W3000403725 countsByYear W30004037252022 @default.
- W3000403725 countsByYear W30004037252023 @default.
- W3000403725 crossrefType "journal-article" @default.
- W3000403725 hasAuthorship W3000403725A5000567490 @default.
- W3000403725 hasAuthorship W3000403725A5079204610 @default.
- W3000403725 hasAuthorship W3000403725A5079602544 @default.
- W3000403725 hasBestOaLocation W30004037251 @default.
- W3000403725 hasConcept C104317684 @default.
- W3000403725 hasConcept C11413529 @default.
- W3000403725 hasConcept C126255220 @default.
- W3000403725 hasConcept C126838900 @default.
- W3000403725 hasConcept C134306372 @default.
- W3000403725 hasConcept C154945302 @default.
- W3000403725 hasConcept C155512373 @default.
- W3000403725 hasConcept C162324750 @default.
- W3000403725 hasConcept C183115368 @default.
- W3000403725 hasConcept C185592680 @default.
- W3000403725 hasConcept C2777303404 @default.
- W3000403725 hasConcept C28826006 @default.
- W3000403725 hasConcept C33923547 @default.
- W3000403725 hasConcept C41008148 @default.
- W3000403725 hasConcept C50522688 @default.
- W3000403725 hasConcept C50644808 @default.
- W3000403725 hasConcept C55493867 @default.
- W3000403725 hasConcept C63479239 @default.
- W3000403725 hasConcept C71924100 @default.
- W3000403725 hasConcept C93779851 @default.
- W3000403725 hasConceptScore W3000403725C104317684 @default.
- W3000403725 hasConceptScore W3000403725C11413529 @default.
- W3000403725 hasConceptScore W3000403725C126255220 @default.
- W3000403725 hasConceptScore W3000403725C126838900 @default.
- W3000403725 hasConceptScore W3000403725C134306372 @default.
- W3000403725 hasConceptScore W3000403725C154945302 @default.
- W3000403725 hasConceptScore W3000403725C155512373 @default.
- W3000403725 hasConceptScore W3000403725C162324750 @default.
- W3000403725 hasConceptScore W3000403725C183115368 @default.
- W3000403725 hasConceptScore W3000403725C185592680 @default.
- W3000403725 hasConceptScore W3000403725C2777303404 @default.
- W3000403725 hasConceptScore W3000403725C28826006 @default.
- W3000403725 hasConceptScore W3000403725C33923547 @default.
- W3000403725 hasConceptScore W3000403725C41008148 @default.
- W3000403725 hasConceptScore W3000403725C50522688 @default.
- W3000403725 hasConceptScore W3000403725C50644808 @default.
- W3000403725 hasConceptScore W3000403725C55493867 @default.
- W3000403725 hasConceptScore W3000403725C63479239 @default.
- W3000403725 hasConceptScore W3000403725C71924100 @default.
- W3000403725 hasConceptScore W3000403725C93779851 @default.
- W3000403725 hasFunder F4320306076 @default.
- W3000403725 hasFunder F4320320751 @default.
- W3000403725 hasFunder F4320321001 @default.