Matches in SemOpenAlex for { <https://semopenalex.org/work/W2906904540> ?p ?o ?g. }
- W2906904540 endingPage "21" @default.
- W2906904540 startingPage "12" @default.
- W2906904540 abstract "We introduce a theory-driven mechanism for learning a neural network model that performs generative topology design in one shot given a problem setting, circumventing the conventional iterative process that computational design tasks usually entail. The proposed mechanism can lead to machines that quickly response to new design requirements based on its knowledge accumulated through past experiences of design generation. Achieving such a mechanism through supervised learning would require an impractically large amount of problem-solution pairs for training, due to the known limitation of deep neural networks in knowledge generalization. To this end, we introduce an interaction between a student (the neural network) and a teacher (the optimality conditions underlying topology optimization): The student learns from existing data and is tested on unseen problems. Deviation of the student's solutions from the optimality conditions is quantified, and used for choosing new data points to learn from. We call this learning mechanism theory-driven, as it explicitly uses domain-specific theories to guide the learning, thus distinguishing itself from purely data-driven supervised learning. We show through a compliance minimization problem that the proposed learning mechanism leads to topology generation with near-optimal structural compliance, much improved from standard supervised learning under the same computational budget." @default.
- W2906904540 created "2019-01-11" @default.
- W2906904540 creator A5038879550 @default.
- W2906904540 creator A5057827568 @default.
- W2906904540 creator A5060501596 @default.
- W2906904540 date "2019-04-01" @default.
- W2906904540 modified "2023-10-16" @default.
- W2906904540 title "One-shot generation of near-optimal topology through theory-driven machine learning" @default.
- W2906904540 cites W1979168015 @default.
- W2906904540 cites W1984823902 @default.
- W2906904540 cites W1996997838 @default.
- W2906904540 cites W1999284878 @default.
- W2906904540 cites W2016413885 @default.
- W2906904540 cites W2023555453 @default.
- W2906904540 cites W2024021823 @default.
- W2906904540 cites W2062523101 @default.
- W2906904540 cites W2069697210 @default.
- W2906904540 cites W2079294419 @default.
- W2906904540 cites W2086674516 @default.
- W2906904540 cites W2090570958 @default.
- W2906904540 cites W2128380429 @default.
- W2906904540 cites W2145680191 @default.
- W2906904540 cites W2165698076 @default.
- W2906904540 cites W2508135389 @default.
- W2906904540 cites W2789526630 @default.
- W2906904540 cites W2950025192 @default.
- W2906904540 cites W2962940229 @default.
- W2906904540 cites W2963580633 @default.
- W2906904540 cites W2963590174 @default.
- W2906904540 cites W3125460488 @default.
- W2906904540 cites W4206723194 @default.
- W2906904540 cites W4235666583 @default.
- W2906904540 doi "https://doi.org/10.1016/j.cad.2018.12.008" @default.
- W2906904540 hasPublicationYear "2019" @default.
- W2906904540 type Work @default.
- W2906904540 sameAs 2906904540 @default.
- W2906904540 citedByCount "41" @default.
- W2906904540 countsByYear W29069045402019 @default.
- W2906904540 countsByYear W29069045402020 @default.
- W2906904540 countsByYear W29069045402021 @default.
- W2906904540 countsByYear W29069045402022 @default.
- W2906904540 countsByYear W29069045402023 @default.
- W2906904540 crossrefType "journal-article" @default.
- W2906904540 hasAuthorship W2906904540A5038879550 @default.
- W2906904540 hasAuthorship W2906904540A5057827568 @default.
- W2906904540 hasAuthorship W2906904540A5060501596 @default.
- W2906904540 hasBestOaLocation W29069045402 @default.
- W2906904540 hasConcept C111472728 @default.
- W2906904540 hasConcept C111919701 @default.
- W2906904540 hasConcept C114614502 @default.
- W2906904540 hasConcept C119857082 @default.
- W2906904540 hasConcept C127413603 @default.
- W2906904540 hasConcept C134306372 @default.
- W2906904540 hasConcept C135628077 @default.
- W2906904540 hasConcept C138885662 @default.
- W2906904540 hasConcept C147764199 @default.
- W2906904540 hasConcept C154945302 @default.
- W2906904540 hasConcept C177148314 @default.
- W2906904540 hasConcept C184720557 @default.
- W2906904540 hasConcept C189216461 @default.
- W2906904540 hasConcept C199360897 @default.
- W2906904540 hasConcept C199845137 @default.
- W2906904540 hasConcept C33923547 @default.
- W2906904540 hasConcept C36503486 @default.
- W2906904540 hasConcept C41008148 @default.
- W2906904540 hasConcept C50644808 @default.
- W2906904540 hasConcept C66938386 @default.
- W2906904540 hasConcept C89611455 @default.
- W2906904540 hasConcept C98045186 @default.
- W2906904540 hasConceptScore W2906904540C111472728 @default.
- W2906904540 hasConceptScore W2906904540C111919701 @default.
- W2906904540 hasConceptScore W2906904540C114614502 @default.
- W2906904540 hasConceptScore W2906904540C119857082 @default.
- W2906904540 hasConceptScore W2906904540C127413603 @default.
- W2906904540 hasConceptScore W2906904540C134306372 @default.
- W2906904540 hasConceptScore W2906904540C135628077 @default.
- W2906904540 hasConceptScore W2906904540C138885662 @default.
- W2906904540 hasConceptScore W2906904540C147764199 @default.
- W2906904540 hasConceptScore W2906904540C154945302 @default.
- W2906904540 hasConceptScore W2906904540C177148314 @default.
- W2906904540 hasConceptScore W2906904540C184720557 @default.
- W2906904540 hasConceptScore W2906904540C189216461 @default.
- W2906904540 hasConceptScore W2906904540C199360897 @default.
- W2906904540 hasConceptScore W2906904540C199845137 @default.
- W2906904540 hasConceptScore W2906904540C33923547 @default.
- W2906904540 hasConceptScore W2906904540C36503486 @default.
- W2906904540 hasConceptScore W2906904540C41008148 @default.
- W2906904540 hasConceptScore W2906904540C50644808 @default.
- W2906904540 hasConceptScore W2906904540C66938386 @default.
- W2906904540 hasConceptScore W2906904540C89611455 @default.
- W2906904540 hasConceptScore W2906904540C98045186 @default.
- W2906904540 hasLocation W29069045401 @default.
- W2906904540 hasLocation W29069045402 @default.
- W2906904540 hasOpenAccess W2906904540 @default.
- W2906904540 hasPrimaryLocation W29069045401 @default.
- W2906904540 hasRelatedWork W2046675961 @default.
- W2906904540 hasRelatedWork W2316061288 @default.
- W2906904540 hasRelatedWork W2381570533 @default.