Matches in SemOpenAlex for { <https://semopenalex.org/work/W3200301644> ?p ?o ?g. }
Showing items 1 to 72 of
72
with 100 items per page.
- W3200301644 abstract "Deep clustering is an emerging topic in deep learning where traditional clustering is performed in deep learning feature space. However, clustering and deep learning are often mutually exclusive. In the autoencoder based deep clustering, the challenge is how to jointly optimize both clustering and dimension reduction together, so that the weights in the hidden layers are not only guided by reconstruction loss, but also by a loss function associated with clustering. The current state-of-the-art has two fundamental flaws. First, they rely on the mathematical convenience of Kullback-Leibler divergence for the clustering loss function but the former is asymmetric. Secondly, they assume the prior knowledge on the number of clusters is always available for their dataset of interest. This paper tries to improve on these problems. In the first problem, we use a Jensen-Shannon divergence to overcome the asymmetric issue, specifically using a closed form variant. Next, we introduce an infinite cluster representation using Dirichlet process Gaussian mixture model for joint clustering and model selection in the latent space which we called deep model selection. The number of clusters in the latent space are not fixed but instead vary accordingly as they gradually approach the optimal number during training. Thus, prior knowledge is not required. We evaluate our proposed deep model selection method with traditional model selection on large class number datasets such as MIT67 and CIFAR100 and also compare with both traditional variational Bayes model and deep clustering method with convincing results." @default.
- W3200301644 created "2021-09-27" @default.
- W3200301644 creator A5087657164 @default.
- W3200301644 date "2021-07-18" @default.
- W3200301644 modified "2023-09-26" @default.
- W3200301644 title "Deep Clustering using Dirichlet Process Gaussian Mixture" @default.
- W3200301644 cites W2100495367 @default.
- W3200301644 cites W2169658215 @default.
- W3200301644 cites W2502114474 @default.
- W3200301644 cites W2730106296 @default.
- W3200301644 cites W2767734436 @default.
- W3200301644 cites W2798534672 @default.
- W3200301644 cites W2803804323 @default.
- W3200301644 cites W2807998075 @default.
- W3200301644 cites W2883725317 @default.
- W3200301644 cites W2884851420 @default.
- W3200301644 cites W2948398419 @default.
- W3200301644 cites W2953791858 @default.
- W3200301644 cites W2964118618 @default.
- W3200301644 cites W2986063762 @default.
- W3200301644 cites W2999320175 @default.
- W3200301644 cites W3003837024 @default.
- W3200301644 cites W3101380508 @default.
- W3200301644 cites W3102206498 @default.
- W3200301644 doi "https://doi.org/10.1109/ijcnn52387.2021.9533366" @default.
- W3200301644 hasPublicationYear "2021" @default.
- W3200301644 type Work @default.
- W3200301644 sameAs 3200301644 @default.
- W3200301644 citedByCount "0" @default.
- W3200301644 crossrefType "proceedings-article" @default.
- W3200301644 hasAuthorship W3200301644A5087657164 @default.
- W3200301644 hasConcept C101738243 @default.
- W3200301644 hasConcept C108583219 @default.
- W3200301644 hasConcept C119857082 @default.
- W3200301644 hasConcept C153180895 @default.
- W3200301644 hasConcept C154945302 @default.
- W3200301644 hasConcept C17212007 @default.
- W3200301644 hasConcept C184509293 @default.
- W3200301644 hasConcept C41008148 @default.
- W3200301644 hasConcept C61224824 @default.
- W3200301644 hasConcept C73555534 @default.
- W3200301644 hasConcept C94641424 @default.
- W3200301644 hasConcept C97385483 @default.
- W3200301644 hasConceptScore W3200301644C101738243 @default.
- W3200301644 hasConceptScore W3200301644C108583219 @default.
- W3200301644 hasConceptScore W3200301644C119857082 @default.
- W3200301644 hasConceptScore W3200301644C153180895 @default.
- W3200301644 hasConceptScore W3200301644C154945302 @default.
- W3200301644 hasConceptScore W3200301644C17212007 @default.
- W3200301644 hasConceptScore W3200301644C184509293 @default.
- W3200301644 hasConceptScore W3200301644C41008148 @default.
- W3200301644 hasConceptScore W3200301644C61224824 @default.
- W3200301644 hasConceptScore W3200301644C73555534 @default.
- W3200301644 hasConceptScore W3200301644C94641424 @default.
- W3200301644 hasConceptScore W3200301644C97385483 @default.
- W3200301644 hasLocation W32003016441 @default.
- W3200301644 hasOpenAccess W3200301644 @default.
- W3200301644 hasPrimaryLocation W32003016441 @default.
- W3200301644 hasRelatedWork W10015831 @default.
- W3200301644 hasRelatedWork W10304599 @default.
- W3200301644 hasRelatedWork W11512698 @default.
- W3200301644 hasRelatedWork W13112433 @default.
- W3200301644 hasRelatedWork W2237909 @default.
- W3200301644 hasRelatedWork W2786405 @default.
- W3200301644 hasRelatedWork W3737758 @default.
- W3200301644 hasRelatedWork W496720 @default.
- W3200301644 hasRelatedWork W6854689 @default.
- W3200301644 hasRelatedWork W7027326 @default.
- W3200301644 isParatext "false" @default.
- W3200301644 isRetracted "false" @default.
- W3200301644 magId "3200301644" @default.
- W3200301644 workType "article" @default.