FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2950863313> ?p ?o ?g. }

• W2950863313 abstract "We propose a method to optimize the representation and distinguishability of samples from two probability distributions, by maximizing the estimated power of a statistical test based on the maximum mean discrepancy (MMD). This optimized MMD is applied to the setting of unsupervised learning by generative adversarial networks (GAN), in which a model attempts to generate realistic samples, and a discriminator attempts to tell these apart from data samples. In this context, the MMD may be used in two roles: first, as a discriminator, either directly on the samples, or on features of the samples. Second, the MMD can be used to evaluate the performance of a generative model, by testing the model's samples against a reference data set. In the latter role, the optimized MMD is particularly helpful, as it gives an interpretable indication of how the model and data distributions differ, even in cases where individual model samples are not easily distinguished either by eye or by classifier." @default.
• W2950863313 created "2019-06-27" @default.
• W2950863313 creator A5004160420 @default.
• W2950863313 creator A5007973437 @default.
• W2950863313 creator A5028602246 @default.
• W2950863313 creator A5030128034 @default.
• W2950863313 creator A5032389695 @default.
• W2950863313 creator A5087204274 @default.
• W2950863313 creator A5090351022 @default.
• W2950863313 date "2016-11-14" @default.
• W2950863313 modified "2023-09-27" @default.
• W2950863313 title "Generative Models and Model Criticism via Optimized Maximum Mean Discrepancy" @default.
• W2950863313 cites W1557650897 @default.
• W2950863313 cites W1571975558 @default.
• W2950863313 cites W1710476689 @default.
• W2950863313 cites W182691100 @default.
• W2950863313 cites W2000992741 @default.
• W2950863313 cites W2006501157 @default.
• W2950863313 cites W2099471712 @default.
• W2950863313 cites W2100600008 @default.
• W2950863313 cites W2101809379 @default.
• W2950863313 cites W2106439909 @default.
• W2950863313 cites W2110097068 @default.
• W2950863313 cites W2110176078 @default.
• W2950863313 cites W2111181349 @default.
• W2950863313 cites W2124331852 @default.
• W2950863313 cites W2174424190 @default.
• W2950863313 cites W2183704914 @default.
• W2950863313 cites W2212660284 @default.
• W2950863313 cites W2217964046 @default.
• W2950863313 cites W2256178860 @default.
• W2950863313 cites W2328111639 @default.
• W2950863313 cites W2797333853 @default.
• W2950863313 cites W2949353404 @default.
• W2950863313 cites W2950292946 @default.
• W2950863313 cites W2963321603 @default.
• W2950863313 cites W2963373786 @default.
• W2950863313 cites W2963800509 @default.
• W2950863313 cites W2963857374 @default.
• W2950863313 cites W2964121744 @default.
• W2950863313 cites W2964340499 @default.
• W2950863313 cites W3126536233 @default.
• W2950863313 cites W648143168 @default.
• W2950863313 cites W930928758 @default.
• W2950863313 hasPublicationYear "2016" @default.
• W2950863313 type Work @default.
• W2950863313 sameAs 2950863313 @default.
• W2950863313 citedByCount "62" @default.
• W2950863313 countsByYear W29508633132016 @default.
• W2950863313 countsByYear W29508633132017 @default.
• W2950863313 countsByYear W29508633132018 @default.
• W2950863313 countsByYear W29508633132019 @default.
• W2950863313 countsByYear W29508633132020 @default.
• W2950863313 countsByYear W29508633132021 @default.
• W2950863313 crossrefType "posted-content" @default.
• W2950863313 hasAuthorship W2950863313A5004160420 @default.
• W2950863313 hasAuthorship W2950863313A5007973437 @default.
• W2950863313 hasAuthorship W2950863313A5028602246 @default.
• W2950863313 hasAuthorship W2950863313A5030128034 @default.
• W2950863313 hasAuthorship W2950863313A5032389695 @default.
• W2950863313 hasAuthorship W2950863313A5087204274 @default.
• W2950863313 hasAuthorship W2950863313A5090351022 @default.
• W2950863313 hasConcept C119857082 @default.
• W2950863313 hasConcept C151730666 @default.
• W2950863313 hasConcept C153180895 @default.
• W2950863313 hasConcept C154945302 @default.
• W2950863313 hasConcept C167966045 @default.
• W2950863313 hasConcept C17744445 @default.
• W2950863313 hasConcept C199539241 @default.
• W2950863313 hasConcept C2776359362 @default.
• W2950863313 hasConcept C2779343474 @default.
• W2950863313 hasConcept C2779803651 @default.
• W2950863313 hasConcept C39890363 @default.
• W2950863313 hasConcept C41008148 @default.
• W2950863313 hasConcept C58489278 @default.
• W2950863313 hasConcept C76155785 @default.
• W2950863313 hasConcept C86803240 @default.
• W2950863313 hasConcept C94625758 @default.
• W2950863313 hasConcept C94915269 @default.
• W2950863313 hasConcept C95623464 @default.
• W2950863313 hasConceptScore W2950863313C119857082 @default.
• W2950863313 hasConceptScore W2950863313C151730666 @default.
• W2950863313 hasConceptScore W2950863313C153180895 @default.
• W2950863313 hasConceptScore W2950863313C154945302 @default.
• W2950863313 hasConceptScore W2950863313C167966045 @default.
• W2950863313 hasConceptScore W2950863313C17744445 @default.
• W2950863313 hasConceptScore W2950863313C199539241 @default.
• W2950863313 hasConceptScore W2950863313C2776359362 @default.
• W2950863313 hasConceptScore W2950863313C2779343474 @default.
• W2950863313 hasConceptScore W2950863313C2779803651 @default.
• W2950863313 hasConceptScore W2950863313C39890363 @default.
• W2950863313 hasConceptScore W2950863313C41008148 @default.
• W2950863313 hasConceptScore W2950863313C58489278 @default.
• W2950863313 hasConceptScore W2950863313C76155785 @default.
• W2950863313 hasConceptScore W2950863313C86803240 @default.
• W2950863313 hasConceptScore W2950863313C94625758 @default.
• W2950863313 hasConceptScore W2950863313C94915269 @default.
• W2950863313 hasConceptScore W2950863313C95623464 @default.
• W2950863313 hasLocation W29508633131 @default.
• W2950863313 hasOpenAccess W2950863313 @default.

• next