Matches in SemOpenAlex for { <https://semopenalex.org/work/W201302718> ?p ?o ?g. }
Showing items 1 to 72 of
72
with 100 items per page.
- W201302718 endingPage "136" @default.
- W201302718 startingPage "117" @default.
- W201302718 abstract "Deep neural networks (DNNs) have many hidden layers each of which has many neurons. This greatly increases the total number of parameters in the model and slows down both the training and decoding. In this chapter, we discuss algorithms and engineering techniques that speedup the training and decoding. Specifically, we describe the parallel training algorithms such as pipelined backpropagation algorithm, asynchronous stochastic gradient descend algorithm, and augmented Lagrange multiplier algorithm. We also introduce model size reduction techniques based on low-rank approximation which can speedup both training and decoding, and techniques such as quantization, lazy evaluation, and frame skipping that significantly speedup the decoding." @default.
- W201302718 created "2016-06-24" @default.
- W201302718 creator A5034476404 @default.
- W201302718 creator A5035017068 @default.
- W201302718 date "2014-11-12" @default.
- W201302718 modified "2023-09-24" @default.
- W201302718 title "Training and Decoding Speedup" @default.
- W201302718 cites W1218987319 @default.
- W201302718 cites W2010291496 @default.
- W201302718 cites W2012257340 @default.
- W201302718 cites W2057624533 @default.
- W201302718 cites W2058641082 @default.
- W201302718 cites W2087402357 @default.
- W201302718 cites W2112984492 @default.
- W201302718 cites W2124653173 @default.
- W201302718 cites W2147768505 @default.
- W201302718 cites W2173213060 @default.
- W201302718 cites W2294370754 @default.
- W201302718 cites W2294543795 @default.
- W201302718 cites W2394932179 @default.
- W201302718 cites W2402040300 @default.
- W201302718 cites W2403195671 @default.
- W201302718 doi "https://doi.org/10.1007/978-1-4471-5779-3_7" @default.
- W201302718 hasPublicationYear "2014" @default.
- W201302718 type Work @default.
- W201302718 sameAs 201302718 @default.
- W201302718 citedByCount "1" @default.
- W201302718 countsByYear W2013027182016 @default.
- W201302718 crossrefType "book-chapter" @default.
- W201302718 hasAuthorship W201302718A5034476404 @default.
- W201302718 hasAuthorship W201302718A5035017068 @default.
- W201302718 hasConcept C11413529 @default.
- W201302718 hasConcept C151319957 @default.
- W201302718 hasConcept C154945302 @default.
- W201302718 hasConcept C155032097 @default.
- W201302718 hasConcept C173608175 @default.
- W201302718 hasConcept C28855332 @default.
- W201302718 hasConcept C31258907 @default.
- W201302718 hasConcept C41008148 @default.
- W201302718 hasConcept C50644808 @default.
- W201302718 hasConcept C57273362 @default.
- W201302718 hasConcept C68339613 @default.
- W201302718 hasConceptScore W201302718C11413529 @default.
- W201302718 hasConceptScore W201302718C151319957 @default.
- W201302718 hasConceptScore W201302718C154945302 @default.
- W201302718 hasConceptScore W201302718C155032097 @default.
- W201302718 hasConceptScore W201302718C173608175 @default.
- W201302718 hasConceptScore W201302718C28855332 @default.
- W201302718 hasConceptScore W201302718C31258907 @default.
- W201302718 hasConceptScore W201302718C41008148 @default.
- W201302718 hasConceptScore W201302718C50644808 @default.
- W201302718 hasConceptScore W201302718C57273362 @default.
- W201302718 hasConceptScore W201302718C68339613 @default.
- W201302718 hasLocation W2013027181 @default.
- W201302718 hasOpenAccess W201302718 @default.
- W201302718 hasPrimaryLocation W2013027181 @default.
- W201302718 hasRelatedWork W1509211761 @default.
- W201302718 hasRelatedWork W1531488649 @default.
- W201302718 hasRelatedWork W1585350690 @default.
- W201302718 hasRelatedWork W2104603305 @default.
- W201302718 hasRelatedWork W2133693067 @default.
- W201302718 hasRelatedWork W2366027386 @default.
- W201302718 hasRelatedWork W2391299576 @default.
- W201302718 hasRelatedWork W2582456645 @default.
- W201302718 hasRelatedWork W4382241230 @default.
- W201302718 hasRelatedWork W2479014312 @default.
- W201302718 isParatext "false" @default.
- W201302718 isRetracted "false" @default.
- W201302718 magId "201302718" @default.
- W201302718 workType "book-chapter" @default.