Matches in SemOpenAlex for { <https://semopenalex.org/work/W2896873306> ?p ?o ?g. }
Showing items 1 to 79 of
79
with 100 items per page.
- W2896873306 endingPage "484" @default.
- W2896873306 startingPage "476" @default.
- W2896873306 abstract "Dense connectivity in latent variable models, recommender systems and deep neural networks make them resource intensive. As the data keeps on growing, the memory and processing requirements also increases. It is not always feasible to extend these physical units hence, tensor methods are used to optimize and improve their performance in a resource constrained environment. Tensors make them fast, accurate and scalable in machine learning however, this results in trade-off between accuracy and resource requirement. In this paper, we explore the feasibility to convert the dense matrices to tensor train format such that number of parameters are reduced and the expressive power of layers are preserved. Based on tensor rank effect observation, a novel decomposition method is proposed which preserves the underlying model’s accuracy along with time and space optimization by tensor methods." @default.
- W2896873306 created "2018-10-26" @default.
- W2896873306 creator A5011262312 @default.
- W2896873306 creator A5027442901 @default.
- W2896873306 creator A5063234710 @default.
- W2896873306 creator A5073150145 @default.
- W2896873306 date "2018-10-10" @default.
- W2896873306 modified "2023-10-18" @default.
- W2896873306 title "Optimal Low Rank Tensor Factorization for Deep Learning" @default.
- W2896873306 cites W1015285300 @default.
- W2896873306 cites W1498436455 @default.
- W2896873306 cites W1963826206 @default.
- W2896873306 cites W1966626570 @default.
- W2896873306 cites W1993482030 @default.
- W2896873306 cites W2022179510 @default.
- W2896873306 cites W2055309977 @default.
- W2896873306 cites W2058641082 @default.
- W2896873306 cites W2081023708 @default.
- W2896873306 cites W2103496339 @default.
- W2896873306 cites W2113165053 @default.
- W2896873306 cites W2136922672 @default.
- W2896873306 cites W2137983211 @default.
- W2896873306 cites W2152332944 @default.
- W2896873306 cites W2294543795 @default.
- W2896873306 cites W2614221804 @default.
- W2896873306 cites W2735553491 @default.
- W2896873306 cites W2963305465 @default.
- W2896873306 cites W4236213345 @default.
- W2896873306 cites W4293052541 @default.
- W2896873306 cites W769100608 @default.
- W2896873306 doi "https://doi.org/10.1007/978-981-13-2372-0_42" @default.
- W2896873306 hasPublicationYear "2018" @default.
- W2896873306 type Work @default.
- W2896873306 sameAs 2896873306 @default.
- W2896873306 citedByCount "0" @default.
- W2896873306 crossrefType "book-chapter" @default.
- W2896873306 hasAuthorship W2896873306A5011262312 @default.
- W2896873306 hasAuthorship W2896873306A5027442901 @default.
- W2896873306 hasAuthorship W2896873306A5063234710 @default.
- W2896873306 hasAuthorship W2896873306A5073150145 @default.
- W2896873306 hasConcept C11413529 @default.
- W2896873306 hasConcept C114614502 @default.
- W2896873306 hasConcept C154945302 @default.
- W2896873306 hasConcept C155281189 @default.
- W2896873306 hasConcept C164226766 @default.
- W2896873306 hasConcept C187834632 @default.
- W2896873306 hasConcept C202444582 @default.
- W2896873306 hasConcept C23123220 @default.
- W2896873306 hasConcept C33923547 @default.
- W2896873306 hasConcept C41008148 @default.
- W2896873306 hasConceptScore W2896873306C11413529 @default.
- W2896873306 hasConceptScore W2896873306C114614502 @default.
- W2896873306 hasConceptScore W2896873306C154945302 @default.
- W2896873306 hasConceptScore W2896873306C155281189 @default.
- W2896873306 hasConceptScore W2896873306C164226766 @default.
- W2896873306 hasConceptScore W2896873306C187834632 @default.
- W2896873306 hasConceptScore W2896873306C202444582 @default.
- W2896873306 hasConceptScore W2896873306C23123220 @default.
- W2896873306 hasConceptScore W2896873306C33923547 @default.
- W2896873306 hasConceptScore W2896873306C41008148 @default.
- W2896873306 hasLocation W28968733061 @default.
- W2896873306 hasOpenAccess W2896873306 @default.
- W2896873306 hasPrimaryLocation W28968733061 @default.
- W2896873306 hasRelatedWork W1576053125 @default.
- W2896873306 hasRelatedWork W2007430971 @default.
- W2896873306 hasRelatedWork W2323887960 @default.
- W2896873306 hasRelatedWork W2970760100 @default.
- W2896873306 hasRelatedWork W2974253572 @default.
- W2896873306 hasRelatedWork W2995838080 @default.
- W2896873306 hasRelatedWork W3088176352 @default.
- W2896873306 hasRelatedWork W3106533591 @default.
- W2896873306 hasRelatedWork W4213058796 @default.
- W2896873306 hasRelatedWork W2556315304 @default.
- W2896873306 isParatext "false" @default.
- W2896873306 isRetracted "false" @default.
- W2896873306 magId "2896873306" @default.
- W2896873306 workType "book-chapter" @default.