Matches in SemOpenAlex for { <https://semopenalex.org/work/W3194300689> ?p ?o ?g. }
Showing items 1 to 98 of
98
with 100 items per page.
- W3194300689 endingPage "110747" @default.
- W3194300689 startingPage "110747" @default.
- W3194300689 abstract "Designing optimal experiments minimizes the uncertainty of results and maximizes the efficient use of resources. Herein, machine learning surrogate models and the approximate coordinate exchange (ACE) algorithm are used to determine optimal experimental designs (OEDs) over large or arbitrarily restrictive design spaces. OED is particularly salient in materials science, where experiments are expensive and material properties must often be inferred indirectly. The proposed framework is demonstrated by finding optimal experiments with which the hidden constituent properties of composite materials can be most efficiently inferred from observable experimental outcomes. The OED is given by an information-theoretic criterion that maximizes the conditional mutual information between the hidden properties and the expected experimental outcomes. To perform tractable optimization, a neural network is trained as a surrogate model to mimic a physics-based simulation, which can calculate the expected experimental outcome based on a candidate experimental design and sampled constituent properties. The ACE algorithm is used to optimize over large design spaces with many tests and controlled parameters where an exhaustive search would be intractable even with the surrogate model. Using this approach, OEDs that are consistent with those produced by heuristic knowledge and established best practices are found; then optimal designs in larger design spaces where heuristic knowledge is unavailable are examined. All code, data, and trained models to reproduce the work in this paper is available at https://github.com/nasa/OED-with-NN-surrogates." @default.
- W3194300689 created "2021-08-30" @default.
- W3194300689 creator A5024602039 @default.
- W3194300689 creator A5072682834 @default.
- W3194300689 creator A5083411746 @default.
- W3194300689 creator A5085735201 @default.
- W3194300689 date "2021-12-01" @default.
- W3194300689 modified "2023-10-14" @default.
- W3194300689 title "Optimal experimental design with fast neural network surrogate models" @default.
- W3194300689 cites W1980443641 @default.
- W3194300689 cites W1992693189 @default.
- W3194300689 cites W2034287504 @default.
- W3194300689 cites W2037855648 @default.
- W3194300689 cites W2040870580 @default.
- W3194300689 cites W2053773352 @default.
- W3194300689 cites W2061482395 @default.
- W3194300689 cites W2070074581 @default.
- W3194300689 cites W2094568847 @default.
- W3194300689 cites W2152690058 @default.
- W3194300689 cites W2167723689 @default.
- W3194300689 cites W2396348748 @default.
- W3194300689 cites W2419572346 @default.
- W3194300689 cites W2461312660 @default.
- W3194300689 cites W2478708596 @default.
- W3194300689 cites W2806634774 @default.
- W3194300689 cites W2990747716 @default.
- W3194300689 cites W3022368615 @default.
- W3194300689 cites W3103297471 @default.
- W3194300689 cites W4241245107 @default.
- W3194300689 cites W2014157487 @default.
- W3194300689 doi "https://doi.org/10.1016/j.commatsci.2021.110747" @default.
- W3194300689 hasPublicationYear "2021" @default.
- W3194300689 type Work @default.
- W3194300689 sameAs 3194300689 @default.
- W3194300689 citedByCount "4" @default.
- W3194300689 countsByYear W31943006892022 @default.
- W3194300689 countsByYear W31943006892023 @default.
- W3194300689 crossrefType "journal-article" @default.
- W3194300689 hasAuthorship W3194300689A5024602039 @default.
- W3194300689 hasAuthorship W3194300689A5072682834 @default.
- W3194300689 hasAuthorship W3194300689A5083411746 @default.
- W3194300689 hasAuthorship W3194300689A5085735201 @default.
- W3194300689 hasBestOaLocation W31943006891 @default.
- W3194300689 hasConcept C105795698 @default.
- W3194300689 hasConcept C11413529 @default.
- W3194300689 hasConcept C119857082 @default.
- W3194300689 hasConcept C126255220 @default.
- W3194300689 hasConcept C131675550 @default.
- W3194300689 hasConcept C154945302 @default.
- W3194300689 hasConcept C173801870 @default.
- W3194300689 hasConcept C177264268 @default.
- W3194300689 hasConcept C186394612 @default.
- W3194300689 hasConcept C199360897 @default.
- W3194300689 hasConcept C2776760102 @default.
- W3194300689 hasConcept C2780719617 @default.
- W3194300689 hasConcept C33923547 @default.
- W3194300689 hasConcept C34559072 @default.
- W3194300689 hasConcept C41008148 @default.
- W3194300689 hasConcept C50644808 @default.
- W3194300689 hasConcept C55037315 @default.
- W3194300689 hasConceptScore W3194300689C105795698 @default.
- W3194300689 hasConceptScore W3194300689C11413529 @default.
- W3194300689 hasConceptScore W3194300689C119857082 @default.
- W3194300689 hasConceptScore W3194300689C126255220 @default.
- W3194300689 hasConceptScore W3194300689C131675550 @default.
- W3194300689 hasConceptScore W3194300689C154945302 @default.
- W3194300689 hasConceptScore W3194300689C173801870 @default.
- W3194300689 hasConceptScore W3194300689C177264268 @default.
- W3194300689 hasConceptScore W3194300689C186394612 @default.
- W3194300689 hasConceptScore W3194300689C199360897 @default.
- W3194300689 hasConceptScore W3194300689C2776760102 @default.
- W3194300689 hasConceptScore W3194300689C2780719617 @default.
- W3194300689 hasConceptScore W3194300689C33923547 @default.
- W3194300689 hasConceptScore W3194300689C34559072 @default.
- W3194300689 hasConceptScore W3194300689C41008148 @default.
- W3194300689 hasConceptScore W3194300689C50644808 @default.
- W3194300689 hasConceptScore W3194300689C55037315 @default.
- W3194300689 hasFunder F4320306101 @default.
- W3194300689 hasLocation W31943006891 @default.
- W3194300689 hasOpenAccess W3194300689 @default.
- W3194300689 hasPrimaryLocation W31943006891 @default.
- W3194300689 hasRelatedWork W1019855432 @default.
- W3194300689 hasRelatedWork W1619946729 @default.
- W3194300689 hasRelatedWork W2390169723 @default.
- W3194300689 hasRelatedWork W2510856016 @default.
- W3194300689 hasRelatedWork W2575519970 @default.
- W3194300689 hasRelatedWork W3033927325 @default.
- W3194300689 hasRelatedWork W3184080862 @default.
- W3194300689 hasRelatedWork W4225667815 @default.
- W3194300689 hasRelatedWork W4288967112 @default.
- W3194300689 hasRelatedWork W4386073189 @default.
- W3194300689 hasVolume "200" @default.
- W3194300689 isParatext "false" @default.
- W3194300689 isRetracted "false" @default.
- W3194300689 magId "3194300689" @default.
- W3194300689 workType "article" @default.