Matches in SemOpenAlex for { <https://semopenalex.org/work/W4380136235> ?p ?o ?g. }
Showing items 1 to 69 of
69
with 100 items per page.
- W4380136235 abstract "The solution of probabilistic inverse problems for which the corresponding forward problem is constrained by physical principles is challenging. This is especially true if the dimension of the inferred vector is large and the prior information about it is in the form of a collection of samples. In this work, a novel deep learning based approach is developed and applied to solving these types of problems. The approach utilizes samples of the inferred vector drawn from the prior distribution and a physics-based forward model to generate training data for a conditional Wasserstein generative adversarial network (cWGAN). The cWGAN learns the probability distribution for the inferred vector conditioned on the measurement and produces samples from this distribution. The cWGAN developed in this work differs from earlier versions in that its critic is required to be 1-Lipschitz with respect to both the inferred and the measurement vectors and not just the former. This leads to a loss term with the full (and not partial) gradient penalty. It is shown that this rather simple change leads to a stronger notion of convergence for the conditional density learned by the cWGAN and a more robust and accurate sampling strategy. Through numerical examples it is shown that this change also translates to better accuracy when solving inverse problems. The numerical examples considered include illustrative problems where the true distribution and/or statistics are known, and a more complex inverse problem motivated by applications in biomechanics." @default.
- W4380136235 created "2023-06-10" @default.
- W4380136235 creator A5031872781 @default.
- W4380136235 creator A5034704499 @default.
- W4380136235 creator A5042325005 @default.
- W4380136235 creator A5065555915 @default.
- W4380136235 date "2023-06-07" @default.
- W4380136235 modified "2023-09-24" @default.
- W4380136235 title "Solution of physics-based inverse problems using conditional generative adversarial networks with full gradient penalty" @default.
- W4380136235 doi "https://doi.org/10.48550/arxiv.2306.04895" @default.
- W4380136235 hasPublicationYear "2023" @default.
- W4380136235 type Work @default.
- W4380136235 citedByCount "0" @default.
- W4380136235 crossrefType "posted-content" @default.
- W4380136235 hasAuthorship W4380136235A5031872781 @default.
- W4380136235 hasAuthorship W4380136235A5034704499 @default.
- W4380136235 hasAuthorship W4380136235A5042325005 @default.
- W4380136235 hasAuthorship W4380136235A5065555915 @default.
- W4380136235 hasBestOaLocation W43801362351 @default.
- W4380136235 hasConcept C105795698 @default.
- W4380136235 hasConcept C11413529 @default.
- W4380136235 hasConcept C126255220 @default.
- W4380136235 hasConcept C134306372 @default.
- W4380136235 hasConcept C135252773 @default.
- W4380136235 hasConcept C154945302 @default.
- W4380136235 hasConcept C162324750 @default.
- W4380136235 hasConcept C202444582 @default.
- W4380136235 hasConcept C22324862 @default.
- W4380136235 hasConcept C2777303404 @default.
- W4380136235 hasConcept C28826006 @default.
- W4380136235 hasConcept C33676613 @default.
- W4380136235 hasConcept C33923547 @default.
- W4380136235 hasConcept C41008148 @default.
- W4380136235 hasConcept C43555835 @default.
- W4380136235 hasConcept C49937458 @default.
- W4380136235 hasConcept C50522688 @default.
- W4380136235 hasConceptScore W4380136235C105795698 @default.
- W4380136235 hasConceptScore W4380136235C11413529 @default.
- W4380136235 hasConceptScore W4380136235C126255220 @default.
- W4380136235 hasConceptScore W4380136235C134306372 @default.
- W4380136235 hasConceptScore W4380136235C135252773 @default.
- W4380136235 hasConceptScore W4380136235C154945302 @default.
- W4380136235 hasConceptScore W4380136235C162324750 @default.
- W4380136235 hasConceptScore W4380136235C202444582 @default.
- W4380136235 hasConceptScore W4380136235C22324862 @default.
- W4380136235 hasConceptScore W4380136235C2777303404 @default.
- W4380136235 hasConceptScore W4380136235C28826006 @default.
- W4380136235 hasConceptScore W4380136235C33676613 @default.
- W4380136235 hasConceptScore W4380136235C33923547 @default.
- W4380136235 hasConceptScore W4380136235C41008148 @default.
- W4380136235 hasConceptScore W4380136235C43555835 @default.
- W4380136235 hasConceptScore W4380136235C49937458 @default.
- W4380136235 hasConceptScore W4380136235C50522688 @default.
- W4380136235 hasLocation W43801362351 @default.
- W4380136235 hasOpenAccess W4380136235 @default.
- W4380136235 hasPrimaryLocation W43801362351 @default.
- W4380136235 hasRelatedWork W1970358763 @default.
- W4380136235 hasRelatedWork W2063845753 @default.
- W4380136235 hasRelatedWork W2152713700 @default.
- W4380136235 hasRelatedWork W2182726851 @default.
- W4380136235 hasRelatedWork W2312248459 @default.
- W4380136235 hasRelatedWork W2343305867 @default.
- W4380136235 hasRelatedWork W2352053904 @default.
- W4380136235 hasRelatedWork W2809189737 @default.
- W4380136235 hasRelatedWork W3038055344 @default.
- W4380136235 hasRelatedWork W2996186043 @default.
- W4380136235 isParatext "false" @default.
- W4380136235 isRetracted "false" @default.
- W4380136235 workType "article" @default.