Matches in SemOpenAlex for { <https://semopenalex.org/work/W3033143012> ?p ?o ?g. }
Showing items 1 to 100 of
100
with 100 items per page.
- W3033143012 abstract "Deep clustering algorithms combine representation learning and clustering by jointly optimizing a clustering loss and a non-clustering loss. In such methods, a deep neural network is used for representation learning together with a clustering network. Instead of following this framework to improve clustering performance, we propose a simpler approach of optimizing the entanglement of the learned latent code representation of an autoencoder. We define entanglement as how close pairs of points from the same class or structure are, relative to pairs of points from different classes or structures. To measure the entanglement of data points, we use the soft nearest neighbor loss, and expand it by introducing an annealing temperature factor. Using our proposed approach, the test clustering accuracy was 96.2% on the MNIST dataset, 85.6% on the Fashion-MNIST dataset, and 79.2% on the EMNIST Balanced dataset, outperforming our baseline models." @default.
- W3033143012 created "2020-06-12" @default.
- W3033143012 creator A5003380343 @default.
- W3033143012 creator A5065131156 @default.
- W3033143012 date "2020-06-05" @default.
- W3033143012 modified "2023-09-23" @default.
- W3033143012 title "Improving k-Means Clustering Performance with Disentangled Internal Representations" @default.
- W3033143012 cites W1665214252 @default.
- W3033143012 cites W1677182931 @default.
- W3033143012 cites W1686810756 @default.
- W3033143012 cites W1959608418 @default.
- W3033143012 cites W1987971958 @default.
- W3033143012 cites W2001141328 @default.
- W3033143012 cites W2051224630 @default.
- W3033143012 cites W205159212 @default.
- W3033143012 cites W2073459066 @default.
- W3033143012 cites W2085487226 @default.
- W3033143012 cites W2099471712 @default.
- W3033143012 cites W2112796928 @default.
- W3033143012 cites W2129066856 @default.
- W3033143012 cites W2129793592 @default.
- W3033143012 cites W2144935315 @default.
- W3033143012 cites W2150593711 @default.
- W3033143012 cites W2163605009 @default.
- W3033143012 cites W2171029115 @default.
- W3033143012 cites W2187089797 @default.
- W3033143012 cites W2194775991 @default.
- W3033143012 cites W2263490141 @default.
- W3033143012 cites W2730106296 @default.
- W3033143012 cites W2734358244 @default.
- W3033143012 cites W2750384547 @default.
- W3033143012 cites W2786672974 @default.
- W3033143012 cites W2953102540 @default.
- W3033143012 cites W2963761396 @default.
- W3033143012 cites W2964074409 @default.
- W3033143012 cites W2964121744 @default.
- W3033143012 cites W2967954196 @default.
- W3033143012 cites W3118608800 @default.
- W3033143012 hasPublicationYear "2020" @default.
- W3033143012 type Work @default.
- W3033143012 sameAs 3033143012 @default.
- W3033143012 citedByCount "0" @default.
- W3033143012 crossrefType "posted-content" @default.
- W3033143012 hasAuthorship W3033143012A5003380343 @default.
- W3033143012 hasAuthorship W3033143012A5065131156 @default.
- W3033143012 hasConcept C101738243 @default.
- W3033143012 hasConcept C119857082 @default.
- W3033143012 hasConcept C124101348 @default.
- W3033143012 hasConcept C153180895 @default.
- W3033143012 hasConcept C154945302 @default.
- W3033143012 hasConcept C17744445 @default.
- W3033143012 hasConcept C190502265 @default.
- W3033143012 hasConcept C199539241 @default.
- W3033143012 hasConcept C2776359362 @default.
- W3033143012 hasConcept C33704608 @default.
- W3033143012 hasConcept C41008148 @default.
- W3033143012 hasConcept C50644808 @default.
- W3033143012 hasConcept C73555534 @default.
- W3033143012 hasConcept C94625758 @default.
- W3033143012 hasConcept C94641424 @default.
- W3033143012 hasConceptScore W3033143012C101738243 @default.
- W3033143012 hasConceptScore W3033143012C119857082 @default.
- W3033143012 hasConceptScore W3033143012C124101348 @default.
- W3033143012 hasConceptScore W3033143012C153180895 @default.
- W3033143012 hasConceptScore W3033143012C154945302 @default.
- W3033143012 hasConceptScore W3033143012C17744445 @default.
- W3033143012 hasConceptScore W3033143012C190502265 @default.
- W3033143012 hasConceptScore W3033143012C199539241 @default.
- W3033143012 hasConceptScore W3033143012C2776359362 @default.
- W3033143012 hasConceptScore W3033143012C33704608 @default.
- W3033143012 hasConceptScore W3033143012C41008148 @default.
- W3033143012 hasConceptScore W3033143012C50644808 @default.
- W3033143012 hasConceptScore W3033143012C73555534 @default.
- W3033143012 hasConceptScore W3033143012C94625758 @default.
- W3033143012 hasConceptScore W3033143012C94641424 @default.
- W3033143012 hasOpenAccess W3033143012 @default.
- W3033143012 hasRelatedWork W1534748669 @default.
- W3033143012 hasRelatedWork W2154295859 @default.
- W3033143012 hasRelatedWork W2156305067 @default.
- W3033143012 hasRelatedWork W2198331616 @default.
- W3033143012 hasRelatedWork W2558860428 @default.
- W3033143012 hasRelatedWork W2742050142 @default.
- W3033143012 hasRelatedWork W2898233200 @default.
- W3033143012 hasRelatedWork W2911208170 @default.
- W3033143012 hasRelatedWork W2980471860 @default.
- W3033143012 hasRelatedWork W2982520178 @default.
- W3033143012 hasRelatedWork W2998134809 @default.
- W3033143012 hasRelatedWork W2999246302 @default.
- W3033143012 hasRelatedWork W3026409547 @default.
- W3033143012 hasRelatedWork W3035575892 @default.
- W3033143012 hasRelatedWork W3048265046 @default.
- W3033143012 hasRelatedWork W3089195948 @default.
- W3033143012 hasRelatedWork W3091075457 @default.
- W3033143012 hasRelatedWork W3099744893 @default.
- W3033143012 hasRelatedWork W3102376457 @default.
- W3033143012 hasRelatedWork W3130174365 @default.
- W3033143012 isParatext "false" @default.
- W3033143012 isRetracted "false" @default.
- W3033143012 magId "3033143012" @default.
- W3033143012 workType "article" @default.