Matches in SemOpenAlex for { <https://semopenalex.org/work/W4386043940> ?p ?o ?g. }
Showing items 1 to 67 of
67
with 100 items per page.
- W4386043940 abstract "Many modern-day applications require the development of new materials with specific properties. In particular, the design of new glass compositions is of great industrial interest. Current machine learning methods for learning the composition-property relationship of glasses promise to save on expensive trial-and-error approaches. Even though quite large datasets on the composition of glasses and their properties already exist (i.e., with more than 350,000 samples), they cover only a very small fraction of the space of all possible glass compositions. This limits the applicability of purely data-driven models for property prediction purposes and necessitates the development of models with high extrapolation power. In this paper, we propose a neural network model which incorporates prior scientific and expert knowledge in its learning pipeline. This informed learning approach leads to an improved extrapolation power compared to blind (uninformed) neural network models. To demonstrate this, we train our models to predict three different material properties, that is, the glass transition temperature, the Young's modulus (at room temperature), and the shear modulus of binary oxide glasses which do not contain sodium. As representatives for conventional blind neural network approaches we use five different feed-forward neural networks of varying widths and depths. For each property, we set up model ensembles of multiple trained models and show that, on average, our proposed informed model performs better in extrapolating the three properties of previously unseen sodium borate glass samples than all five conventional blind models." @default.
- W4386043940 created "2023-08-22" @default.
- W4386043940 creator A5010757293 @default.
- W4386043940 creator A5061134483 @default.
- W4386043940 creator A5085518222 @default.
- W4386043940 creator A5092671721 @default.
- W4386043940 date "2023-08-18" @default.
- W4386043940 modified "2023-09-25" @default.
- W4386043940 title "Predicting Properties of Oxide Glasses Using Informed Neural Networks" @default.
- W4386043940 doi "https://doi.org/10.48550/arxiv.2308.09492" @default.
- W4386043940 hasPublicationYear "2023" @default.
- W4386043940 type Work @default.
- W4386043940 citedByCount "0" @default.
- W4386043940 crossrefType "posted-content" @default.
- W4386043940 hasAuthorship W4386043940A5010757293 @default.
- W4386043940 hasAuthorship W4386043940A5061134483 @default.
- W4386043940 hasAuthorship W4386043940A5085518222 @default.
- W4386043940 hasAuthorship W4386043940A5092671721 @default.
- W4386043940 hasBestOaLocation W43860439401 @default.
- W4386043940 hasConcept C105795698 @default.
- W4386043940 hasConcept C111472728 @default.
- W4386043940 hasConcept C119857082 @default.
- W4386043940 hasConcept C132459708 @default.
- W4386043940 hasConcept C138885662 @default.
- W4386043940 hasConcept C154945302 @default.
- W4386043940 hasConcept C177264268 @default.
- W4386043940 hasConcept C189950617 @default.
- W4386043940 hasConcept C191897082 @default.
- W4386043940 hasConcept C192562407 @default.
- W4386043940 hasConcept C199360897 @default.
- W4386043940 hasConcept C2778111025 @default.
- W4386043940 hasConcept C2779851234 @default.
- W4386043940 hasConcept C33923547 @default.
- W4386043940 hasConcept C41008148 @default.
- W4386043940 hasConcept C50644808 @default.
- W4386043940 hasConceptScore W4386043940C105795698 @default.
- W4386043940 hasConceptScore W4386043940C111472728 @default.
- W4386043940 hasConceptScore W4386043940C119857082 @default.
- W4386043940 hasConceptScore W4386043940C132459708 @default.
- W4386043940 hasConceptScore W4386043940C138885662 @default.
- W4386043940 hasConceptScore W4386043940C154945302 @default.
- W4386043940 hasConceptScore W4386043940C177264268 @default.
- W4386043940 hasConceptScore W4386043940C189950617 @default.
- W4386043940 hasConceptScore W4386043940C191897082 @default.
- W4386043940 hasConceptScore W4386043940C192562407 @default.
- W4386043940 hasConceptScore W4386043940C199360897 @default.
- W4386043940 hasConceptScore W4386043940C2778111025 @default.
- W4386043940 hasConceptScore W4386043940C2779851234 @default.
- W4386043940 hasConceptScore W4386043940C33923547 @default.
- W4386043940 hasConceptScore W4386043940C41008148 @default.
- W4386043940 hasConceptScore W4386043940C50644808 @default.
- W4386043940 hasLocation W43860439401 @default.
- W4386043940 hasOpenAccess W4386043940 @default.
- W4386043940 hasPrimaryLocation W43860439401 @default.
- W4386043940 hasRelatedWork W2012884882 @default.
- W4386043940 hasRelatedWork W2089686343 @default.
- W4386043940 hasRelatedWork W2134948224 @default.
- W4386043940 hasRelatedWork W2414885887 @default.
- W4386043940 hasRelatedWork W2899084033 @default.
- W4386043940 hasRelatedWork W2961085424 @default.
- W4386043940 hasRelatedWork W4286629047 @default.
- W4386043940 hasRelatedWork W4306674287 @default.
- W4386043940 hasRelatedWork W4385965578 @default.
- W4386043940 hasRelatedWork W4224009465 @default.
- W4386043940 isParatext "false" @default.
- W4386043940 isRetracted "false" @default.
- W4386043940 workType "article" @default.