FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3000384001> ?p ?o ?g. }

• W3000384001 endingPage "374" @default.
• W3000384001 startingPage "361" @default.
• W3000384001 abstract "This work introduces an optimal transportation (OT) view of generative adversarial networks (GANs). Natural datasets have intrinsic patterns, which can be summarized as the manifold distribution principle: the distribution of a class of data is close to a low-dimensional manifold. GANs mainly accomplish two tasks: manifold learning and probability distribution transformation. The latter can be carried out using the classical OT method. From the OT perspective, the generator computes the OT map, while the discriminator computes the Wasserstein distance between the generated data distribution and the real data distribution; both can be reduced to a convex geometric optimization process. Furthermore, OT theory discovers the intrinsic collaborative—instead of competitive—relation between the generator and the discriminator, and the fundamental reason for mode collapse. We also propose a novel generative model, which uses an autoencoder (AE) for manifold learning and OT map for probability distribution transformation. This AE–OT model improves the theoretical rigor and transparency, as well as the computational stability and efficiency; in particular, it eliminates the mode collapse. The experimental results validate our hypothesis, and demonstrate the advantages of our proposed model." @default.
• W3000384001 created "2020-01-23" @default.
• W3000384001 creator A5006865040 @default.
• W3000384001 creator A5035967128 @default.
• W3000384001 creator A5038775008 @default.
• W3000384001 creator A5045140275 @default.
• W3000384001 creator A5049677402 @default.
• W3000384001 creator A5066195167 @default.
• W3000384001 creator A5086990531 @default.
• W3000384001 creator A5089570452 @default.
• W3000384001 date "2020-03-01" @default.
• W3000384001 modified "2023-10-18" @default.
• W3000384001 title "A Geometric Understanding of Deep Learning" @default.
• W3000384001 cites W1575501403 @default.
• W3000384001 cites W2001141328 @default.
• W3000384001 cites W2009172320 @default.
• W3000384001 cites W2028852533 @default.
• W3000384001 cites W2038392026 @default.
• W3000384001 cites W2052643735 @default.
• W3000384001 cites W2068013644 @default.
• W3000384001 cites W2098770975 @default.
• W3000384001 cites W2117553576 @default.
• W3000384001 cites W2132883347 @default.
• W3000384001 cites W2172275395 @default.
• W3000384001 cites W2962929605 @default.
• W3000384001 cites W2963875852 @default.
• W3000384001 cites W2964268141 @default.
• W3000384001 cites W2964347177 @default.
• W3000384001 cites W4206471589 @default.
• W3000384001 doi "https://doi.org/10.1016/j.eng.2019.09.010" @default.
• W3000384001 hasPublicationYear "2020" @default.
• W3000384001 type Work @default.
• W3000384001 sameAs 3000384001 @default.
• W3000384001 citedByCount "56" @default.
• W3000384001 countsByYear W30003840012020 @default.
• W3000384001 countsByYear W30003840012021 @default.
• W3000384001 countsByYear W30003840012022 @default.
• W3000384001 countsByYear W30003840012023 @default.
• W3000384001 crossrefType "journal-article" @default.
• W3000384001 hasAuthorship W3000384001A5006865040 @default.
• W3000384001 hasAuthorship W3000384001A5035967128 @default.
• W3000384001 hasAuthorship W3000384001A5038775008 @default.
• W3000384001 hasAuthorship W3000384001A5045140275 @default.
• W3000384001 hasAuthorship W3000384001A5049677402 @default.
• W3000384001 hasAuthorship W3000384001A5066195167 @default.
• W3000384001 hasAuthorship W3000384001A5086990531 @default.
• W3000384001 hasAuthorship W3000384001A5089570452 @default.
• W3000384001 hasBestOaLocation W30003840011 @default.
• W3000384001 hasConcept C101738243 @default.
• W3000384001 hasConcept C104317684 @default.
• W3000384001 hasConcept C105795698 @default.
• W3000384001 hasConcept C111919701 @default.
• W3000384001 hasConcept C112972136 @default.
• W3000384001 hasConcept C11413529 @default.
• W3000384001 hasConcept C119857082 @default.
• W3000384001 hasConcept C121332964 @default.
• W3000384001 hasConcept C127413603 @default.
• W3000384001 hasConcept C138885662 @default.
• W3000384001 hasConcept C149441793 @default.
• W3000384001 hasConcept C151876577 @default.
• W3000384001 hasConcept C153120616 @default.
• W3000384001 hasConcept C154945302 @default.
• W3000384001 hasConcept C163258240 @default.
• W3000384001 hasConcept C167966045 @default.
• W3000384001 hasConcept C185592680 @default.
• W3000384001 hasConcept C204241405 @default.
• W3000384001 hasConcept C207390915 @default.
• W3000384001 hasConcept C2779803651 @default.
• W3000384001 hasConcept C2780992000 @default.
• W3000384001 hasConcept C33923547 @default.
• W3000384001 hasConcept C39890363 @default.
• W3000384001 hasConcept C41008148 @default.
• W3000384001 hasConcept C41895202 @default.
• W3000384001 hasConcept C48677424 @default.
• W3000384001 hasConcept C50644808 @default.
• W3000384001 hasConcept C529865628 @default.
• W3000384001 hasConcept C55493867 @default.
• W3000384001 hasConcept C62520636 @default.
• W3000384001 hasConcept C70518039 @default.
• W3000384001 hasConcept C76155785 @default.
• W3000384001 hasConcept C78519656 @default.
• W3000384001 hasConcept C94915269 @default.
• W3000384001 hasConceptScore W3000384001C101738243 @default.
• W3000384001 hasConceptScore W3000384001C104317684 @default.
• W3000384001 hasConceptScore W3000384001C105795698 @default.
• W3000384001 hasConceptScore W3000384001C111919701 @default.
• W3000384001 hasConceptScore W3000384001C112972136 @default.
• W3000384001 hasConceptScore W3000384001C11413529 @default.
• W3000384001 hasConceptScore W3000384001C119857082 @default.
• W3000384001 hasConceptScore W3000384001C121332964 @default.
• W3000384001 hasConceptScore W3000384001C127413603 @default.
• W3000384001 hasConceptScore W3000384001C138885662 @default.
• W3000384001 hasConceptScore W3000384001C149441793 @default.
• W3000384001 hasConceptScore W3000384001C151876577 @default.
• W3000384001 hasConceptScore W3000384001C153120616 @default.
• W3000384001 hasConceptScore W3000384001C154945302 @default.
• W3000384001 hasConceptScore W3000384001C163258240 @default.
• W3000384001 hasConceptScore W3000384001C167966045 @default.

• next