Matches in SemOpenAlex for { <https://semopenalex.org/work/W3034266300> ?p ?o ?g. }
Showing items 1 to 85 of
85
with 100 items per page.
- W3034266300 abstract "We present a visualization algorithm based on a novel unsupervised Siamese neural network training regime and loss function, called Differentiating Embedding Networks (DEN). The Siamese neural network finds differentiating or similar features between specific pairs of samples in a dataset, and uses these features to embed the dataset in a lower dimensional space where it can be visualized. Unlike existing visualization algorithms such as UMAP or $t$-SNE, DEN is parametric, meaning it can be interpreted by techniques such as SHAP. To interpret DEN, we create an end-to-end parametric clustering algorithm on top of the visualization, and then leverage SHAP scores to determine which features in the sample space are important for understanding the structures shown in the visualization based on the clusters found. We compare DEN visualizations with existing techniques on a variety of datasets, including image and scRNA-seq data. We then show that our clustering algorithm performs similarly to the state of the art despite not having prior knowledge of the number of clusters, and sets a new state of the art on FashionMNIST. Finally, we demonstrate finding differentiating features of a dataset. Code available at this https URL" @default.
- W3034266300 created "2020-06-19" @default.
- W3034266300 creator A5055970768 @default.
- W3034266300 date "2020-06-11" @default.
- W3034266300 modified "2023-09-27" @default.
- W3034266300 title "Interpretable Visualizations with Differentiating Embedding Networks" @default.
- W3034266300 cites W1698699930 @default.
- W3034266300 cites W1970432641 @default.
- W3034266300 cites W2073459066 @default.
- W3034266300 cites W2097922870 @default.
- W3034266300 cites W2100659887 @default.
- W3034266300 cites W2112545207 @default.
- W3034266300 cites W2112796928 @default.
- W3034266300 cites W2187089797 @default.
- W3034266300 cites W2420245003 @default.
- W3034266300 cites W2510746232 @default.
- W3034266300 cites W2601243251 @default.
- W3034266300 cites W2624413595 @default.
- W3034266300 cites W2750384547 @default.
- W3034266300 cites W2781711557 @default.
- W3034266300 cites W2962852342 @default.
- W3034266300 cites W2963318411 @default.
- W3034266300 cites W2963626623 @default.
- W3034266300 cites W2963761396 @default.
- W3034266300 cites W2967954196 @default.
- W3034266300 cites W3040712465 @default.
- W3034266300 cites W3091905774 @default.
- W3034266300 cites W3105146463 @default.
- W3034266300 cites W953353200 @default.
- W3034266300 hasPublicationYear "2020" @default.
- W3034266300 type Work @default.
- W3034266300 sameAs 3034266300 @default.
- W3034266300 citedByCount "1" @default.
- W3034266300 countsByYear W30342663002020 @default.
- W3034266300 crossrefType "posted-content" @default.
- W3034266300 hasAuthorship W3034266300A5055970768 @default.
- W3034266300 hasConcept C119857082 @default.
- W3034266300 hasConcept C124101348 @default.
- W3034266300 hasConcept C153083717 @default.
- W3034266300 hasConcept C153180895 @default.
- W3034266300 hasConcept C154945302 @default.
- W3034266300 hasConcept C172367668 @default.
- W3034266300 hasConcept C36464697 @default.
- W3034266300 hasConcept C41008148 @default.
- W3034266300 hasConcept C41608201 @default.
- W3034266300 hasConcept C50644808 @default.
- W3034266300 hasConcept C73555534 @default.
- W3034266300 hasConceptScore W3034266300C119857082 @default.
- W3034266300 hasConceptScore W3034266300C124101348 @default.
- W3034266300 hasConceptScore W3034266300C153083717 @default.
- W3034266300 hasConceptScore W3034266300C153180895 @default.
- W3034266300 hasConceptScore W3034266300C154945302 @default.
- W3034266300 hasConceptScore W3034266300C172367668 @default.
- W3034266300 hasConceptScore W3034266300C36464697 @default.
- W3034266300 hasConceptScore W3034266300C41008148 @default.
- W3034266300 hasConceptScore W3034266300C41608201 @default.
- W3034266300 hasConceptScore W3034266300C50644808 @default.
- W3034266300 hasConceptScore W3034266300C73555534 @default.
- W3034266300 hasLocation W30342663001 @default.
- W3034266300 hasOpenAccess W3034266300 @default.
- W3034266300 hasPrimaryLocation W30342663001 @default.
- W3034266300 hasRelatedWork W1986471197 @default.
- W3034266300 hasRelatedWork W1994754807 @default.
- W3034266300 hasRelatedWork W2005948381 @default.
- W3034266300 hasRelatedWork W2040226816 @default.
- W3034266300 hasRelatedWork W2076915 @default.
- W3034266300 hasRelatedWork W2102505380 @default.
- W3034266300 hasRelatedWork W2115791769 @default.
- W3034266300 hasRelatedWork W2134933642 @default.
- W3034266300 hasRelatedWork W2157530472 @default.
- W3034266300 hasRelatedWork W2169177915 @default.
- W3034266300 hasRelatedWork W2183544714 @default.
- W3034266300 hasRelatedWork W2316762422 @default.
- W3034266300 hasRelatedWork W2509845068 @default.
- W3034266300 hasRelatedWork W2731832604 @default.
- W3034266300 hasRelatedWork W2795226127 @default.
- W3034266300 hasRelatedWork W2903393357 @default.
- W3034266300 hasRelatedWork W3024460019 @default.
- W3034266300 hasRelatedWork W3089451348 @default.
- W3034266300 hasRelatedWork W3092923617 @default.
- W3034266300 hasRelatedWork W3195399758 @default.
- W3034266300 isParatext "false" @default.
- W3034266300 isRetracted "false" @default.
- W3034266300 magId "3034266300" @default.
- W3034266300 workType "article" @default.