Matches in SemOpenAlex for { <https://semopenalex.org/work/W3210152748> ?p ?o ?g. }
Showing items 1 to 98 of
98
with 100 items per page.
- W3210152748 abstract "Using neural networks to solve variational problems, and other scientific machine learning tasks, has been limited by a lack of consistency and an inability to exactly integrate expressions involving neural network architectures. We address these limitations by formulating a novel neural network architecture that combines a polynomial mixture-of-experts model with free knot B1-spline basis functions. Effectively, our architecture performs piecewise polynomial approximation on each cell of a trainable partition of unity. Our architecture exhibits both $h$- and $p$- refinement for regression problems at the convergence rates expected from approximation theory, allowing for consistency in solving variational problems. Moreover, this architecture, its moments, and its partial derivatives can all be integrated exactly, obviating a reliance on sampling or quadrature and enabling error-free computation of variational forms. We demonstrate the success of our network on a range of regression and variational problems that illustrate the consistency and exact integrability of our network architecture." @default.
- W3210152748 created "2021-11-08" @default.
- W3210152748 creator A5012538860 @default.
- W3210152748 creator A5040611179 @default.
- W3210152748 creator A5056314900 @default.
- W3210152748 date "2021-10-26" @default.
- W3210152748 modified "2023-10-17" @default.
- W3210152748 title "Polynomial-Spline Neural Networks with Exact Integrals" @default.
- W3210152748 cites W129017765 @default.
- W3210152748 cites W1989594010 @default.
- W3210152748 cites W2065451462 @default.
- W3210152748 cites W2067596735 @default.
- W3210152748 cites W2068238590 @default.
- W3210152748 cites W2212370034 @default.
- W3210152748 cites W2760972773 @default.
- W3210152748 cites W2792013640 @default.
- W3210152748 cites W2803629276 @default.
- W3210152748 cites W280536263 @default.
- W3210152748 cites W2899283552 @default.
- W3210152748 cites W2962782102 @default.
- W3210152748 cites W2964121744 @default.
- W3210152748 cites W2977465327 @default.
- W3210152748 cites W2999467285 @default.
- W3210152748 cites W3021722416 @default.
- W3210152748 cites W3099849883 @default.
- W3210152748 cites W3099878876 @default.
- W3210152748 cites W3102139197 @default.
- W3210152748 cites W3112297092 @default.
- W3210152748 cites W73123583 @default.
- W3210152748 hasPublicationYear "2021" @default.
- W3210152748 type Work @default.
- W3210152748 sameAs 3210152748 @default.
- W3210152748 citedByCount "0" @default.
- W3210152748 crossrefType "posted-content" @default.
- W3210152748 hasAuthorship W3210152748A5012538860 @default.
- W3210152748 hasAuthorship W3210152748A5040611179 @default.
- W3210152748 hasAuthorship W3210152748A5056314900 @default.
- W3210152748 hasConcept C10390562 @default.
- W3210152748 hasConcept C11413529 @default.
- W3210152748 hasConcept C119599485 @default.
- W3210152748 hasConcept C126255220 @default.
- W3210152748 hasConcept C127413603 @default.
- W3210152748 hasConcept C134306372 @default.
- W3210152748 hasConcept C154945302 @default.
- W3210152748 hasConcept C164660894 @default.
- W3210152748 hasConcept C2776436953 @default.
- W3210152748 hasConcept C28826006 @default.
- W3210152748 hasConcept C33923547 @default.
- W3210152748 hasConcept C41008148 @default.
- W3210152748 hasConcept C45374587 @default.
- W3210152748 hasConcept C50644808 @default.
- W3210152748 hasConcept C62869609 @default.
- W3210152748 hasConcept C66938386 @default.
- W3210152748 hasConcept C90119067 @default.
- W3210152748 hasConceptScore W3210152748C10390562 @default.
- W3210152748 hasConceptScore W3210152748C11413529 @default.
- W3210152748 hasConceptScore W3210152748C119599485 @default.
- W3210152748 hasConceptScore W3210152748C126255220 @default.
- W3210152748 hasConceptScore W3210152748C127413603 @default.
- W3210152748 hasConceptScore W3210152748C134306372 @default.
- W3210152748 hasConceptScore W3210152748C154945302 @default.
- W3210152748 hasConceptScore W3210152748C164660894 @default.
- W3210152748 hasConceptScore W3210152748C2776436953 @default.
- W3210152748 hasConceptScore W3210152748C28826006 @default.
- W3210152748 hasConceptScore W3210152748C33923547 @default.
- W3210152748 hasConceptScore W3210152748C41008148 @default.
- W3210152748 hasConceptScore W3210152748C45374587 @default.
- W3210152748 hasConceptScore W3210152748C50644808 @default.
- W3210152748 hasConceptScore W3210152748C62869609 @default.
- W3210152748 hasConceptScore W3210152748C66938386 @default.
- W3210152748 hasConceptScore W3210152748C90119067 @default.
- W3210152748 hasLocation W32101527481 @default.
- W3210152748 hasOpenAccess W3210152748 @default.
- W3210152748 hasPrimaryLocation W32101527481 @default.
- W3210152748 hasRelatedWork W1572697379 @default.
- W3210152748 hasRelatedWork W1991859114 @default.
- W3210152748 hasRelatedWork W2042729862 @default.
- W3210152748 hasRelatedWork W2528188058 @default.
- W3210152748 hasRelatedWork W2726495480 @default.
- W3210152748 hasRelatedWork W2998001803 @default.
- W3210152748 hasRelatedWork W3005055065 @default.
- W3210152748 hasRelatedWork W3007410779 @default.
- W3210152748 hasRelatedWork W3013319227 @default.
- W3210152748 hasRelatedWork W3025785221 @default.
- W3210152748 hasRelatedWork W3041514420 @default.
- W3210152748 hasRelatedWork W3048106789 @default.
- W3210152748 hasRelatedWork W3096437864 @default.
- W3210152748 hasRelatedWork W3108952918 @default.
- W3210152748 hasRelatedWork W3112068713 @default.
- W3210152748 hasRelatedWork W3113111988 @default.
- W3210152748 hasRelatedWork W3156750472 @default.
- W3210152748 hasRelatedWork W3160447895 @default.
- W3210152748 hasRelatedWork W3194828218 @default.
- W3210152748 hasRelatedWork W3207223734 @default.
- W3210152748 isParatext "false" @default.
- W3210152748 isRetracted "false" @default.
- W3210152748 magId "3210152748" @default.
- W3210152748 workType "article" @default.