Matches in SemOpenAlex for { <https://semopenalex.org/work/W2783260025> ?p ?o ?g. }
- W2783260025 endingPage "55" @default.
- W2783260025 startingPage "31" @default.
- W2783260025 abstract "Most clustering algorithms are designed to minimize a distortion measure which quantifies how far the elements of the clusters are from their respective centroids. The assessment of the results is often carried out with the help of cluster quality measures which take into account the compactness and separation of the clusters. However, these measures are not amenable to optimization because they are not differentiable with respect to the centroids even for a given set of clusters. Here we propose a differentiable cluster quality measure, and an associated clustering algorithm to optimize it. It turns out that the standard k-means algorithm is a special case of our method. Experimental results are reported with both synthetic and real datasets, which demonstrate the performance of our approach with respect to several standard quantitative measures." @default.
- W2783260025 created "2018-01-26" @default.
- W2783260025 creator A5000003467 @default.
- W2783260025 creator A5085558846 @default.
- W2783260025 creator A5091243468 @default.
- W2783260025 date "2018-04-01" @default.
- W2783260025 modified "2023-09-30" @default.
- W2783260025 title "Unsupervised learning by cluster quality optimization" @default.
- W2783260025 cites W1975331922 @default.
- W2783260025 cites W1977103328 @default.
- W2783260025 cites W1979607399 @default.
- W2783260025 cites W1981566656 @default.
- W2783260025 cites W1987019005 @default.
- W2783260025 cites W1989544085 @default.
- W2783260025 cites W1990367006 @default.
- W2783260025 cites W1990368529 @default.
- W2783260025 cites W1991645955 @default.
- W2783260025 cites W1994638866 @default.
- W2783260025 cites W2011430131 @default.
- W2783260025 cites W2045893432 @default.
- W2783260025 cites W2051224630 @default.
- W2783260025 cites W2074560087 @default.
- W2783260025 cites W2096166399 @default.
- W2783260025 cites W2108154570 @default.
- W2783260025 cites W2120529703 @default.
- W2783260025 cites W2120688485 @default.
- W2783260025 cites W2125070513 @default.
- W2783260025 cites W2126751256 @default.
- W2783260025 cites W2130926326 @default.
- W2783260025 cites W2131994307 @default.
- W2783260025 cites W2132914434 @default.
- W2783260025 cites W2137446479 @default.
- W2783260025 cites W2138810473 @default.
- W2783260025 cites W2142827986 @default.
- W2783260025 cites W2159091719 @default.
- W2783260025 cites W2160172739 @default.
- W2783260025 cites W2160396543 @default.
- W2783260025 cites W2161160262 @default.
- W2783260025 cites W2164331655 @default.
- W2783260025 cites W2171074980 @default.
- W2783260025 cites W2171975443 @default.
- W2783260025 cites W2330904790 @default.
- W2783260025 cites W2418455592 @default.
- W2783260025 doi "https://doi.org/10.1016/j.ins.2018.01.007" @default.
- W2783260025 hasPublicationYear "2018" @default.
- W2783260025 type Work @default.
- W2783260025 sameAs 2783260025 @default.
- W2783260025 citedByCount "12" @default.
- W2783260025 countsByYear W27832600252019 @default.
- W2783260025 countsByYear W27832600252020 @default.
- W2783260025 countsByYear W27832600252021 @default.
- W2783260025 countsByYear W27832600252022 @default.
- W2783260025 countsByYear W27832600252023 @default.
- W2783260025 crossrefType "journal-article" @default.
- W2783260025 hasAuthorship W2783260025A5000003467 @default.
- W2783260025 hasAuthorship W2783260025A5085558846 @default.
- W2783260025 hasAuthorship W2783260025A5091243468 @default.
- W2783260025 hasConcept C111472728 @default.
- W2783260025 hasConcept C11413529 @default.
- W2783260025 hasConcept C124101348 @default.
- W2783260025 hasConcept C126780896 @default.
- W2783260025 hasConcept C134306372 @default.
- W2783260025 hasConcept C138885662 @default.
- W2783260025 hasConcept C146599234 @default.
- W2783260025 hasConcept C153180895 @default.
- W2783260025 hasConcept C154945302 @default.
- W2783260025 hasConcept C164866538 @default.
- W2783260025 hasConcept C177264268 @default.
- W2783260025 hasConcept C18648836 @default.
- W2783260025 hasConcept C194257627 @default.
- W2783260025 hasConcept C199360897 @default.
- W2783260025 hasConcept C202444582 @default.
- W2783260025 hasConcept C202615002 @default.
- W2783260025 hasConcept C207968372 @default.
- W2783260025 hasConcept C2776257435 @default.
- W2783260025 hasConcept C2779530757 @default.
- W2783260025 hasConcept C2780009758 @default.
- W2783260025 hasConcept C31258907 @default.
- W2783260025 hasConcept C33923547 @default.
- W2783260025 hasConcept C41008148 @default.
- W2783260025 hasConcept C73555534 @default.
- W2783260025 hasConceptScore W2783260025C111472728 @default.
- W2783260025 hasConceptScore W2783260025C11413529 @default.
- W2783260025 hasConceptScore W2783260025C124101348 @default.
- W2783260025 hasConceptScore W2783260025C126780896 @default.
- W2783260025 hasConceptScore W2783260025C134306372 @default.
- W2783260025 hasConceptScore W2783260025C138885662 @default.
- W2783260025 hasConceptScore W2783260025C146599234 @default.
- W2783260025 hasConceptScore W2783260025C153180895 @default.
- W2783260025 hasConceptScore W2783260025C154945302 @default.
- W2783260025 hasConceptScore W2783260025C164866538 @default.
- W2783260025 hasConceptScore W2783260025C177264268 @default.
- W2783260025 hasConceptScore W2783260025C18648836 @default.
- W2783260025 hasConceptScore W2783260025C194257627 @default.
- W2783260025 hasConceptScore W2783260025C199360897 @default.
- W2783260025 hasConceptScore W2783260025C202444582 @default.
- W2783260025 hasConceptScore W2783260025C202615002 @default.
- W2783260025 hasConceptScore W2783260025C207968372 @default.