Matches in SemOpenAlex for { <https://semopenalex.org/work/W4386348024> ?p ?o ?g. }
Showing items 1 to 83 of
83
with 100 items per page.
- W4386348024 abstract "Generative Adversarial Networks (GANs) should produce synthetic data that fits the underlying distribution of the data being modeled. For real valued time-series data, this implies the need to simultaneously capture the static distribution of the data, but also the full temporal distribution of the data for any potential time horizon. This temporal element produces a more complex problem that can potentially leave current solutions under-constrained, unstable during training, or prone to varying degrees of mode collapse. In FETSGAN, entire sequences are translated directly to the generator's sampling space using a seq2seq style adversarial auto encoder (AAE), where adversarial training is used to match the training distribution in both the feature space and the lower dimensional sampling space. This additional constraint provides a loose assurance that the temporal distribution of the synthetic samples will not collapse. In addition, the First Above Threshold (FAT) operator is introduced to supplement the reconstruction of encoded sequences, which improves training stability and the overall quality of the synthetic data being generated. These novel contributions demonstrate a significant improvement to the current state of the art for adversarial learners in qualitative measures of temporal similarity and quantitative predictive ability of data generated through FETSGAN." @default.
- W4386348024 created "2023-09-02" @default.
- W4386348024 creator A5001150648 @default.
- W4386348024 creator A5046607346 @default.
- W4386348024 date "2023-08-29" @default.
- W4386348024 modified "2023-09-28" @default.
- W4386348024 title "Fully Embedded Time-Series Generative Adversarial Networks" @default.
- W4386348024 doi "https://doi.org/10.48550/arxiv.2308.15730" @default.
- W4386348024 hasPublicationYear "2023" @default.
- W4386348024 type Work @default.
- W4386348024 citedByCount "0" @default.
- W4386348024 crossrefType "posted-content" @default.
- W4386348024 hasAuthorship W4386348024A5001150648 @default.
- W4386348024 hasAuthorship W4386348024A5046607346 @default.
- W4386348024 hasBestOaLocation W43863480241 @default.
- W4386348024 hasConcept C103278499 @default.
- W4386348024 hasConcept C106131492 @default.
- W4386348024 hasConcept C112972136 @default.
- W4386348024 hasConcept C11413529 @default.
- W4386348024 hasConcept C115961682 @default.
- W4386348024 hasConcept C119857082 @default.
- W4386348024 hasConcept C121332964 @default.
- W4386348024 hasConcept C140779682 @default.
- W4386348024 hasConcept C143724316 @default.
- W4386348024 hasConcept C151406439 @default.
- W4386348024 hasConcept C151730666 @default.
- W4386348024 hasConcept C153180895 @default.
- W4386348024 hasConcept C154945302 @default.
- W4386348024 hasConcept C163258240 @default.
- W4386348024 hasConcept C2524010 @default.
- W4386348024 hasConcept C2776036281 @default.
- W4386348024 hasConcept C2780992000 @default.
- W4386348024 hasConcept C31972630 @default.
- W4386348024 hasConcept C33923547 @default.
- W4386348024 hasConcept C37736160 @default.
- W4386348024 hasConcept C39890363 @default.
- W4386348024 hasConcept C41008148 @default.
- W4386348024 hasConcept C62520636 @default.
- W4386348024 hasConcept C774472 @default.
- W4386348024 hasConcept C83665646 @default.
- W4386348024 hasConcept C86803240 @default.
- W4386348024 hasConceptScore W4386348024C103278499 @default.
- W4386348024 hasConceptScore W4386348024C106131492 @default.
- W4386348024 hasConceptScore W4386348024C112972136 @default.
- W4386348024 hasConceptScore W4386348024C11413529 @default.
- W4386348024 hasConceptScore W4386348024C115961682 @default.
- W4386348024 hasConceptScore W4386348024C119857082 @default.
- W4386348024 hasConceptScore W4386348024C121332964 @default.
- W4386348024 hasConceptScore W4386348024C140779682 @default.
- W4386348024 hasConceptScore W4386348024C143724316 @default.
- W4386348024 hasConceptScore W4386348024C151406439 @default.
- W4386348024 hasConceptScore W4386348024C151730666 @default.
- W4386348024 hasConceptScore W4386348024C153180895 @default.
- W4386348024 hasConceptScore W4386348024C154945302 @default.
- W4386348024 hasConceptScore W4386348024C163258240 @default.
- W4386348024 hasConceptScore W4386348024C2524010 @default.
- W4386348024 hasConceptScore W4386348024C2776036281 @default.
- W4386348024 hasConceptScore W4386348024C2780992000 @default.
- W4386348024 hasConceptScore W4386348024C31972630 @default.
- W4386348024 hasConceptScore W4386348024C33923547 @default.
- W4386348024 hasConceptScore W4386348024C37736160 @default.
- W4386348024 hasConceptScore W4386348024C39890363 @default.
- W4386348024 hasConceptScore W4386348024C41008148 @default.
- W4386348024 hasConceptScore W4386348024C62520636 @default.
- W4386348024 hasConceptScore W4386348024C774472 @default.
- W4386348024 hasConceptScore W4386348024C83665646 @default.
- W4386348024 hasConceptScore W4386348024C86803240 @default.
- W4386348024 hasLocation W43863480241 @default.
- W4386348024 hasOpenAccess W4386348024 @default.
- W4386348024 hasPrimaryLocation W43863480241 @default.
- W4386348024 hasRelatedWork W2476099471 @default.
- W4386348024 hasRelatedWork W2561036008 @default.
- W4386348024 hasRelatedWork W2900055988 @default.
- W4386348024 hasRelatedWork W2914998939 @default.
- W4386348024 hasRelatedWork W3005700414 @default.
- W4386348024 hasRelatedWork W3005996785 @default.
- W4386348024 hasRelatedWork W3156291593 @default.
- W4386348024 hasRelatedWork W3198184493 @default.
- W4386348024 hasRelatedWork W4288624664 @default.
- W4386348024 hasRelatedWork W4289303600 @default.
- W4386348024 isParatext "false" @default.
- W4386348024 isRetracted "false" @default.
- W4386348024 workType "article" @default.