Matches in SemOpenAlex for { <https://semopenalex.org/work/W4311595144> ?p ?o ?g. }
Showing items 1 to 67 of
67
with 100 items per page.
- W4311595144 abstract "t-distributed stochastic neighbor embedding (t-SNE) is a well-established visualization method for complex high-dimensional data. However, the original t-SNE method is nonparametric, stochastic, and often cannot well prevserve the global structure of data as it emphasizes local neighborhood. With t-SNE as a reference, we propose to combine the deep neural network (DNN) with the mathematical-grounded embedding rules for high-dimensional data embedding. We first introduce a deep embedding network (DEN) framework, which can learn a parametric mapping from high-dimensional space to low-dimensional embedding. DEN has a flexible architecture that can accommodate different input data (vector, image, or tensor) and loss functions. To improve the embedding performance, a recursive training strategy is proposed to make use of the latent representations extracted by DEN. Finally, we propose a two-stage loss function combining the advantages of two popular embedding methods, namely, t-SNE and uniform manifold approximation and projection (UMAP), for optimal visualization effect. We name the proposed method Deep Recursive Embedding (DRE), which optimizes DEN with a recursive training strategy and two-stage losse. Our experiments demonstrated the excellent performance of the proposed DRE method on high-dimensional data embedding, across a variety of public databases. Remarkably, our comparative results suggested that our proposed DRE could lead to improved global structure preservation." @default.
- W4311595144 created "2022-12-27" @default.
- W4311595144 creator A5021757255 @default.
- W4311595144 creator A5032588771 @default.
- W4311595144 creator A5039050598 @default.
- W4311595144 creator A5065418938 @default.
- W4311595144 date "2021-04-11" @default.
- W4311595144 modified "2023-10-16" @default.
- W4311595144 title "Deep Recursive Embedding for High-Dimensional Data" @default.
- W4311595144 doi "https://doi.org/10.48550/arxiv.2104.05171" @default.
- W4311595144 hasPublicationYear "2021" @default.
- W4311595144 type Work @default.
- W4311595144 citedByCount "0" @default.
- W4311595144 crossrefType "posted-content" @default.
- W4311595144 hasAuthorship W4311595144A5021757255 @default.
- W4311595144 hasAuthorship W4311595144A5032588771 @default.
- W4311595144 hasAuthorship W4311595144A5039050598 @default.
- W4311595144 hasAuthorship W4311595144A5065418938 @default.
- W4311595144 hasBestOaLocation W43115951441 @default.
- W4311595144 hasConcept C105795698 @default.
- W4311595144 hasConcept C108583219 @default.
- W4311595144 hasConcept C11413529 @default.
- W4311595144 hasConcept C117251300 @default.
- W4311595144 hasConcept C151876577 @default.
- W4311595144 hasConcept C154945302 @default.
- W4311595144 hasConcept C2778626561 @default.
- W4311595144 hasConcept C33923547 @default.
- W4311595144 hasConcept C36464697 @default.
- W4311595144 hasConcept C41008148 @default.
- W4311595144 hasConcept C41608201 @default.
- W4311595144 hasConcept C50644808 @default.
- W4311595144 hasConcept C57493831 @default.
- W4311595144 hasConcept C70518039 @default.
- W4311595144 hasConcept C80444323 @default.
- W4311595144 hasConceptScore W4311595144C105795698 @default.
- W4311595144 hasConceptScore W4311595144C108583219 @default.
- W4311595144 hasConceptScore W4311595144C11413529 @default.
- W4311595144 hasConceptScore W4311595144C117251300 @default.
- W4311595144 hasConceptScore W4311595144C151876577 @default.
- W4311595144 hasConceptScore W4311595144C154945302 @default.
- W4311595144 hasConceptScore W4311595144C2778626561 @default.
- W4311595144 hasConceptScore W4311595144C33923547 @default.
- W4311595144 hasConceptScore W4311595144C36464697 @default.
- W4311595144 hasConceptScore W4311595144C41008148 @default.
- W4311595144 hasConceptScore W4311595144C41608201 @default.
- W4311595144 hasConceptScore W4311595144C50644808 @default.
- W4311595144 hasConceptScore W4311595144C57493831 @default.
- W4311595144 hasConceptScore W4311595144C70518039 @default.
- W4311595144 hasConceptScore W4311595144C80444323 @default.
- W4311595144 hasLocation W43115951441 @default.
- W4311595144 hasLocation W43115951442 @default.
- W4311595144 hasLocation W43115951443 @default.
- W4311595144 hasOpenAccess W4311595144 @default.
- W4311595144 hasPrimaryLocation W43115951441 @default.
- W4311595144 hasRelatedWork W1594815103 @default.
- W4311595144 hasRelatedWork W1964013853 @default.
- W4311595144 hasRelatedWork W2003710317 @default.
- W4311595144 hasRelatedWork W2032002253 @default.
- W4311595144 hasRelatedWork W207143075 @default.
- W4311595144 hasRelatedWork W2156287497 @default.
- W4311595144 hasRelatedWork W2372437498 @default.
- W4311595144 hasRelatedWork W3124275785 @default.
- W4311595144 hasRelatedWork W4243436042 @default.
- W4311595144 hasRelatedWork W4287375746 @default.
- W4311595144 isParatext "false" @default.
- W4311595144 isRetracted "false" @default.
- W4311595144 workType "article" @default.