Matches in SemOpenAlex for { <https://semopenalex.org/work/W4386101881> ?p ?o ?g. }
Showing items 1 to 99 of
99
with 100 items per page.
- W4386101881 endingPage "112452" @default.
- W4386101881 startingPage "112452" @default.
- W4386101881 abstract "Machine learning has been successfully applied to various fields of scientific computing in recent years. In this work, we propose a sparse radial basis function neural network method to solve elliptic partial differential equations (PDEs) with multiscale coefficients. Inspired by the deep mixed residual method, we rewrite the second-order problem into a first-order system and employ multiple radial basis function neural networks (RBFNNs) to approximate unknown functions in the system. To aviod the overfitting due to the simplicity of RBFNN, an additional regularization is introduced in the loss function. Thus the loss function contains two parts: the $L_2$ loss for the residual of the first-order system and boundary conditions, and the $ell_1$ regularization term for the weights of radial basis functions (RBFs). An algorithm for optimizing the specific loss function is introduced to accelerate the training process. The accuracy and effectiveness of the proposed method are demonstrated through a collection of multiscale problems with scale separation, discontinuity and multiple scales from one to three dimensions. Notably, the $ell_1$ regularization can achieve the goal of representing the solution by fewer RBFs. As a consequence, the total number of RBFs scales like $mathcal{O}(varepsilon^{-ntau})$, where $varepsilon$ is the smallest scale, $n$ is the dimensionality, and $tau$ is typically smaller than $1$. It is worth mentioning that the proposed method not only has the numerical convergence and thus provides a reliable numerical solution in three dimensions when a classical method is typically not affordable, but also outperforms most other available machine learning methods in terms of accuracy and robustness." @default.
- W4386101881 created "2023-08-24" @default.
- W4386101881 creator A5025195102 @default.
- W4386101881 creator A5084816002 @default.
- W4386101881 creator A5088943078 @default.
- W4386101881 date "2023-11-01" @default.
- W4386101881 modified "2023-09-26" @default.
- W4386101881 title "Solving multiscale elliptic problems by sparse radial basis function neural networks" @default.
- W4386101881 cites W1972576201 @default.
- W4386101881 cites W1980404981 @default.
- W4386101881 cites W1990157709 @default.
- W4386101881 cites W1991849741 @default.
- W4386101881 cites W2029918260 @default.
- W4386101881 cites W2092713299 @default.
- W4386101881 cites W2113442785 @default.
- W4386101881 cites W2165173282 @default.
- W4386101881 cites W2168728641 @default.
- W4386101881 cites W2740147847 @default.
- W4386101881 cites W2749028154 @default.
- W4386101881 cites W2760972773 @default.
- W4386101881 cites W2899283552 @default.
- W4386101881 cites W2964110066 @default.
- W4386101881 cites W3045146186 @default.
- W4386101881 cites W3100086694 @default.
- W4386101881 cites W3100666994 @default.
- W4386101881 cites W3103674763 @default.
- W4386101881 cites W3214098784 @default.
- W4386101881 cites W4226402869 @default.
- W4386101881 cites W4283651928 @default.
- W4386101881 doi "https://doi.org/10.1016/j.jcp.2023.112452" @default.
- W4386101881 hasPublicationYear "2023" @default.
- W4386101881 type Work @default.
- W4386101881 citedByCount "0" @default.
- W4386101881 crossrefType "journal-article" @default.
- W4386101881 hasAuthorship W4386101881A5025195102 @default.
- W4386101881 hasAuthorship W4386101881A5084816002 @default.
- W4386101881 hasAuthorship W4386101881A5088943078 @default.
- W4386101881 hasBestOaLocation W43861018812 @default.
- W4386101881 hasConcept C111030470 @default.
- W4386101881 hasConcept C11413529 @default.
- W4386101881 hasConcept C126255220 @default.
- W4386101881 hasConcept C134306372 @default.
- W4386101881 hasConcept C14036430 @default.
- W4386101881 hasConcept C154945302 @default.
- W4386101881 hasConcept C155512373 @default.
- W4386101881 hasConcept C22019652 @default.
- W4386101881 hasConcept C2776135515 @default.
- W4386101881 hasConcept C28826006 @default.
- W4386101881 hasConcept C33923547 @default.
- W4386101881 hasConcept C41008148 @default.
- W4386101881 hasConcept C50644808 @default.
- W4386101881 hasConcept C5917680 @default.
- W4386101881 hasConcept C78458016 @default.
- W4386101881 hasConcept C80269521 @default.
- W4386101881 hasConcept C86803240 @default.
- W4386101881 hasConcept C93779851 @default.
- W4386101881 hasConcept C98856871 @default.
- W4386101881 hasConceptScore W4386101881C111030470 @default.
- W4386101881 hasConceptScore W4386101881C11413529 @default.
- W4386101881 hasConceptScore W4386101881C126255220 @default.
- W4386101881 hasConceptScore W4386101881C134306372 @default.
- W4386101881 hasConceptScore W4386101881C14036430 @default.
- W4386101881 hasConceptScore W4386101881C154945302 @default.
- W4386101881 hasConceptScore W4386101881C155512373 @default.
- W4386101881 hasConceptScore W4386101881C22019652 @default.
- W4386101881 hasConceptScore W4386101881C2776135515 @default.
- W4386101881 hasConceptScore W4386101881C28826006 @default.
- W4386101881 hasConceptScore W4386101881C33923547 @default.
- W4386101881 hasConceptScore W4386101881C41008148 @default.
- W4386101881 hasConceptScore W4386101881C50644808 @default.
- W4386101881 hasConceptScore W4386101881C5917680 @default.
- W4386101881 hasConceptScore W4386101881C78458016 @default.
- W4386101881 hasConceptScore W4386101881C80269521 @default.
- W4386101881 hasConceptScore W4386101881C86803240 @default.
- W4386101881 hasConceptScore W4386101881C93779851 @default.
- W4386101881 hasConceptScore W4386101881C98856871 @default.
- W4386101881 hasFunder F4320316314 @default.
- W4386101881 hasFunder F4320327777 @default.
- W4386101881 hasFunder F4320335777 @default.
- W4386101881 hasLocation W43861018811 @default.
- W4386101881 hasLocation W43861018812 @default.
- W4386101881 hasOpenAccess W4386101881 @default.
- W4386101881 hasPrimaryLocation W43861018811 @default.
- W4386101881 hasRelatedWork W2137046381 @default.
- W4386101881 hasRelatedWork W2146552914 @default.
- W4386101881 hasRelatedWork W2361403305 @default.
- W4386101881 hasRelatedWork W2549635012 @default.
- W4386101881 hasRelatedWork W2731330146 @default.
- W4386101881 hasRelatedWork W2979333396 @default.
- W4386101881 hasRelatedWork W3098175809 @default.
- W4386101881 hasRelatedWork W3111993716 @default.
- W4386101881 hasRelatedWork W3130878122 @default.
- W4386101881 hasRelatedWork W4280592714 @default.
- W4386101881 hasVolume "492" @default.
- W4386101881 isParatext "false" @default.
- W4386101881 isRetracted "false" @default.
- W4386101881 workType "article" @default.