FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3195348523> ?p ?o ?g. }

• W3195348523 endingPage "114079" @default.
• W3195348523 startingPage "114079" @default.
• W3195348523 abstract "Modern machine learning (ML) techniques, in conjunction with simulation-based methods, present remarkable potential for various scientific and engineering applications. Within the materials science field, these data-based methods can be used to build efficient structure–property linkages that can be further integrated within multi-scale simulations, or guide experiments in a materials discovery setting. However, a critical shortcoming of state-of-the-art ML techniques is their lack of reliable uncertainty/error estimates, which severely limits their use for materials or other engineering applications where data is often scarce and uncertainties are substantial. This paper presents methods for Bayesian learning of neural networks (NN) that allow consideration of both aleatoric uncertainties that account for the inherent stochasticity of the data-generating process, and epistemic uncertainties, which arise from consideration of limited amounts of data. In particular, algorithms based on approximate variational inference and (pseudo-)Bayesian model averaging achieve an appropriate trade-off between accuracy of the uncertainty estimates and accessible computational cost. The performance of these algorithms is first presented on simple 1D examples to illustrate their behavior in both extrapolation and interpolation settings. The approach is then applied for the prediction of homogenized and localized properties of a composite material. In this setting, data is generated from a finite element model, which permits a study of the behavior of the probabilistic learning algorithms under various amounts of aleatoric and epistemic uncertainties." @default.
• W3195348523 created "2021-08-30" @default.
• W3195348523 creator A5009832101 @default.
• W3195348523 creator A5041446747 @default.
• W3195348523 creator A5049156729 @default.
• W3195348523 date "2021-12-01" @default.
• W3195348523 modified "2023-10-18" @default.
• W3195348523 title "Bayesian neural networks for uncertainty quantification in data-driven materials modeling" @default.
• W3195348523 cites W1532236978 @default.
• W3195348523 cites W1631618898 @default.
• W3195348523 cites W1994833963 @default.
• W3195348523 cites W2019561942 @default.
• W3195348523 cites W2050053010 @default.
• W3195348523 cites W2085607286 @default.
• W3195348523 cites W2097968133 @default.
• W3195348523 cites W2127301223 @default.
• W3195348523 cites W2130902307 @default.
• W3195348523 cites W2149498546 @default.
• W3195348523 cites W2164524421 @default.
• W3195348523 cites W2189471760 @default.
• W3195348523 cites W2313966941 @default.
• W3195348523 cites W2338402873 @default.
• W3195348523 cites W2464725281 @default.
• W3195348523 cites W2490555771 @default.
• W3195348523 cites W2503343131 @default.
• W3195348523 cites W2562939451 @default.
• W3195348523 cites W2586155783 @default.
• W3195348523 cites W2597626167 @default.
• W3195348523 cites W2742835787 @default.
• W3195348523 cites W2760710953 @default.
• W3195348523 cites W2786232134 @default.
• W3195348523 cites W2794691459 @default.
• W3195348523 cites W2807414627 @default.
• W3195348523 cites W2890968382 @default.
• W3195348523 cites W2897923334 @default.
• W3195348523 cites W2899283552 @default.
• W3195348523 cites W2919115771 @default.
• W3195348523 cites W2922826800 @default.
• W3195348523 cites W2951965145 @default.
• W3195348523 cites W2963807552 @default.
• W3195348523 cites W3010849941 @default.
• W3195348523 cites W3025645353 @default.
• W3195348523 cites W3098407580 @default.
• W3195348523 cites W3099654532 @default.
• W3195348523 cites W571971660 @default.
• W3195348523 doi "https://doi.org/10.1016/j.cma.2021.114079" @default.
• W3195348523 hasPublicationYear "2021" @default.
• W3195348523 type Work @default.
• W3195348523 sameAs 3195348523 @default.
• W3195348523 citedByCount "34" @default.
• W3195348523 countsByYear W31953485232021 @default.
• W3195348523 countsByYear W31953485232022 @default.
• W3195348523 countsByYear W31953485232023 @default.
• W3195348523 crossrefType "journal-article" @default.
• W3195348523 hasAuthorship W3195348523A5009832101 @default.
• W3195348523 hasAuthorship W3195348523A5041446747 @default.
• W3195348523 hasAuthorship W3195348523A5049156729 @default.
• W3195348523 hasBestOaLocation W31953485231 @default.
• W3195348523 hasConcept C104114177 @default.
• W3195348523 hasConcept C107673813 @default.
• W3195348523 hasConcept C111919701 @default.
• W3195348523 hasConcept C11413529 @default.
• W3195348523 hasConcept C119857082 @default.
• W3195348523 hasConcept C124101348 @default.
• W3195348523 hasConcept C132459708 @default.
• W3195348523 hasConcept C134306372 @default.
• W3195348523 hasConcept C137800194 @default.
• W3195348523 hasConcept C154945302 @default.
• W3195348523 hasConcept C160234255 @default.
• W3195348523 hasConcept C2776214188 @default.
• W3195348523 hasConcept C32230216 @default.
• W3195348523 hasConcept C33923547 @default.
• W3195348523 hasConcept C41008148 @default.
• W3195348523 hasConcept C49937458 @default.
• W3195348523 hasConcept C50644808 @default.
• W3195348523 hasConcept C98045186 @default.
• W3195348523 hasConceptScore W3195348523C104114177 @default.
• W3195348523 hasConceptScore W3195348523C107673813 @default.
• W3195348523 hasConceptScore W3195348523C111919701 @default.
• W3195348523 hasConceptScore W3195348523C11413529 @default.
• W3195348523 hasConceptScore W3195348523C119857082 @default.
• W3195348523 hasConceptScore W3195348523C124101348 @default.
• W3195348523 hasConceptScore W3195348523C132459708 @default.
• W3195348523 hasConceptScore W3195348523C134306372 @default.
• W3195348523 hasConceptScore W3195348523C137800194 @default.
• W3195348523 hasConceptScore W3195348523C154945302 @default.
• W3195348523 hasConceptScore W3195348523C160234255 @default.
• W3195348523 hasConceptScore W3195348523C2776214188 @default.
• W3195348523 hasConceptScore W3195348523C32230216 @default.
• W3195348523 hasConceptScore W3195348523C33923547 @default.
• W3195348523 hasConceptScore W3195348523C41008148 @default.
• W3195348523 hasConceptScore W3195348523C49937458 @default.
• W3195348523 hasConceptScore W3195348523C50644808 @default.
• W3195348523 hasConceptScore W3195348523C98045186 @default.
• W3195348523 hasFunder F4320338295 @default.
• W3195348523 hasLocation W31953485231 @default.
• W3195348523 hasOpenAccess W3195348523 @default.
• W3195348523 hasPrimaryLocation W31953485231 @default.

• next