Matches in SemOpenAlex for { <https://semopenalex.org/work/W4293075306> ?p ?o ?g. }
Showing items 1 to 95 of
95
with 100 items per page.
- W4293075306 endingPage "2983" @default.
- W4293075306 startingPage "2970" @default.
- W4293075306 abstract "System design tools are often only available as input–output blackboxes: for a given design as input, they compute an output representing system behavior. Blackboxes are intended to be run in the forward direction. This article presents a new method of solving the “inverse design problem,” namely, given requirements or constraints on output, find an input that also optimizes an objective function. This problem is challenging for several reasons. First, blackboxes are not designed to be run in reverse. Second, inputs and outputs can be discrete and continuous. Third, finding designs concurrently satisfying a set of requirements is hard because designs satisfying individual requirements may conflict with each other. Fourth, blackbox evaluations can be expensive. Finally, evaluations can sometimes fail to produce an output due to nonconvergence of underlying numerical algorithms. This article presents CNMA, a new method of solving the inverse problem that overcomes these challenges. CNMA tries to sample only the part of the design space relevant to solving the inverse problem, leveraging the power of neural networks, mixed-integer linear programs, and a new learning-from-failure feedback loop. This article also presents a parallel version of CNMA that improves the efficiency and quality of solutions over the sequential version and tries to steer it away from local optima. CNMA’s performance is evaluated against conventional optimization methods for seven nonlinear design problems of 8 (two problems), 10, 15, 36 and 60 real-valued dimensions and one with 186 binary dimensions. Conventional methods evaluated are stable, off-the-shelf implementations of the Bayesian optimization with the Gaussian Processes, Nelder–Mead, and Random Search. The first two do not even produce a solution for problems that are high dimensional, having both discrete and continuous variables or whose blackboxes fail to return values for some inputs. CNMA produces solutions for all problems. When conventional methods do produce solutions, CNMA improves upon their performance by 1%–87%." @default.
- W4293075306 created "2022-08-26" @default.
- W4293075306 creator A5006397770 @default.
- W4293075306 creator A5029912955 @default.
- W4293075306 creator A5044251670 @default.
- W4293075306 creator A5056755374 @default.
- W4293075306 creator A5076223289 @default.
- W4293075306 creator A5083913136 @default.
- W4293075306 creator A5086131079 @default.
- W4293075306 date "2022-09-01" @default.
- W4293075306 modified "2023-09-25" @default.
- W4293075306 title "Fast Design Space Exploration of Nonlinear Systems: Part I" @default.
- W4293075306 cites W1738827650 @default.
- W4293075306 cites W1991186968 @default.
- W4293075306 cites W1998150031 @default.
- W4293075306 cites W2036879211 @default.
- W4293075306 cites W2048799772 @default.
- W4293075306 cites W2051423425 @default.
- W4293075306 cites W2051434435 @default.
- W4293075306 cites W2117261126 @default.
- W4293075306 cites W2126105956 @default.
- W4293075306 cites W2160960847 @default.
- W4293075306 cites W2165059292 @default.
- W4293075306 cites W2338548332 @default.
- W4293075306 cites W2560401546 @default.
- W4293075306 cites W2976145414 @default.
- W4293075306 cites W3100043946 @default.
- W4293075306 cites W4210836678 @default.
- W4293075306 cites W4235606958 @default.
- W4293075306 doi "https://doi.org/10.1109/tcad.2021.3118963" @default.
- W4293075306 hasPublicationYear "2022" @default.
- W4293075306 type Work @default.
- W4293075306 citedByCount "4" @default.
- W4293075306 countsByYear W42930753062022 @default.
- W4293075306 countsByYear W42930753062023 @default.
- W4293075306 crossrefType "journal-article" @default.
- W4293075306 hasAuthorship W4293075306A5006397770 @default.
- W4293075306 hasAuthorship W4293075306A5029912955 @default.
- W4293075306 hasAuthorship W4293075306A5044251670 @default.
- W4293075306 hasAuthorship W4293075306A5056755374 @default.
- W4293075306 hasAuthorship W4293075306A5076223289 @default.
- W4293075306 hasAuthorship W4293075306A5083913136 @default.
- W4293075306 hasAuthorship W4293075306A5086131079 @default.
- W4293075306 hasBestOaLocation W42930753062 @default.
- W4293075306 hasConcept C11413529 @default.
- W4293075306 hasConcept C121332964 @default.
- W4293075306 hasConcept C126255220 @default.
- W4293075306 hasConcept C14036430 @default.
- W4293075306 hasConcept C158622935 @default.
- W4293075306 hasConcept C177264268 @default.
- W4293075306 hasConcept C199360897 @default.
- W4293075306 hasConcept C26713055 @default.
- W4293075306 hasConcept C33923547 @default.
- W4293075306 hasConcept C41008148 @default.
- W4293075306 hasConcept C62520636 @default.
- W4293075306 hasConcept C78458016 @default.
- W4293075306 hasConcept C86803240 @default.
- W4293075306 hasConcept C97137487 @default.
- W4293075306 hasConceptScore W4293075306C11413529 @default.
- W4293075306 hasConceptScore W4293075306C121332964 @default.
- W4293075306 hasConceptScore W4293075306C126255220 @default.
- W4293075306 hasConceptScore W4293075306C14036430 @default.
- W4293075306 hasConceptScore W4293075306C158622935 @default.
- W4293075306 hasConceptScore W4293075306C177264268 @default.
- W4293075306 hasConceptScore W4293075306C199360897 @default.
- W4293075306 hasConceptScore W4293075306C26713055 @default.
- W4293075306 hasConceptScore W4293075306C33923547 @default.
- W4293075306 hasConceptScore W4293075306C41008148 @default.
- W4293075306 hasConceptScore W4293075306C62520636 @default.
- W4293075306 hasConceptScore W4293075306C78458016 @default.
- W4293075306 hasConceptScore W4293075306C86803240 @default.
- W4293075306 hasConceptScore W4293075306C97137487 @default.
- W4293075306 hasFunder F4320332180 @default.
- W4293075306 hasFunder F4320338294 @default.
- W4293075306 hasIssue "9" @default.
- W4293075306 hasLocation W42930753061 @default.
- W4293075306 hasLocation W42930753062 @default.
- W4293075306 hasOpenAccess W4293075306 @default.
- W4293075306 hasPrimaryLocation W42930753061 @default.
- W4293075306 hasRelatedWork W1485630101 @default.
- W4293075306 hasRelatedWork W1536235319 @default.
- W4293075306 hasRelatedWork W1575263621 @default.
- W4293075306 hasRelatedWork W1964111820 @default.
- W4293075306 hasRelatedWork W2083338789 @default.
- W4293075306 hasRelatedWork W2132038253 @default.
- W4293075306 hasRelatedWork W2327568262 @default.
- W4293075306 hasRelatedWork W2384497200 @default.
- W4293075306 hasRelatedWork W4244853187 @default.
- W4293075306 hasRelatedWork W2803721528 @default.
- W4293075306 hasVolume "41" @default.
- W4293075306 isParatext "false" @default.
- W4293075306 isRetracted "false" @default.
- W4293075306 workType "article" @default.