Matches in SemOpenAlex for { <https://semopenalex.org/work/W2045183812> ?p ?o ?g. }
Showing items 1 to 93 of
93
with 100 items per page.
- W2045183812 endingPage "2" @default.
- W2045183812 startingPage "1" @default.
- W2045183812 abstract "The world is experiencing a data revolution to discover knowledge in big data. Large scale neural networks are one of the mainstream tools of big data analytics. Processing big data with large scale neural networks includes two phases: the training phase and the operation phase. Huge computing power is required to support the training phase. And the energy efficiency (power efficiency) is one of the major considerations of the operation phase. We first explore the computing power of GPUs for big data analytics and demonstrate an efficient GPU implementation of the training phase of large scale recurrent neural networks (RNNs). We then introduce a promising ultra-high energy efficient implementation of neural networks' operation phase by taking advantage of the emerging memristor technique. Experiment results show that the proposed GPU implementation of RNNs is able to achieve 2 ~ 11× speed-up compared with the basic CPU implementation. And the scaled-up recurrent neural network trained with GPUs realizes an accuracy of 47% on the Microsoft Research Sentence Completion Challenge, the best result achieved by a single RNN on the same dataset. In addition, the proposed memristor-based implementation of neural networks demonstrates power efficiency of > 400 GFLOPS/W and achieves energy savings of 22× on the HMAX model compared with its pure digital implementation counterpart." @default.
- W2045183812 created "2016-06-24" @default.
- W2045183812 creator A5054900679 @default.
- W2045183812 creator A5058073627 @default.
- W2045183812 creator A5059222136 @default.
- W2045183812 creator A5065452238 @default.
- W2045183812 creator A5079594267 @default.
- W2045183812 creator A5085347958 @default.
- W2045183812 date "2014-03-24" @default.
- W2045183812 modified "2023-09-23" @default.
- W2045183812 title "Energy efficient neural networks for big data analytics" @default.
- W2045183812 cites W1772447446 @default.
- W2045183812 cites W196214544 @default.
- W2045183812 cites W1976075132 @default.
- W2045183812 cites W2067658794 @default.
- W2045183812 cites W2080451019 @default.
- W2045183812 cites W2097732278 @default.
- W2045183812 cites W2102017903 @default.
- W2045183812 cites W2162390675 @default.
- W2045183812 cites W2168231600 @default.
- W2045183812 cites W2170503676 @default.
- W2045183812 cites W2474824677 @default.
- W2045183812 doi "https://doi.org/10.5555/2616606.2617095" @default.
- W2045183812 hasPublicationYear "2014" @default.
- W2045183812 type Work @default.
- W2045183812 sameAs 2045183812 @default.
- W2045183812 citedByCount "2" @default.
- W2045183812 countsByYear W20451838122018 @default.
- W2045183812 countsByYear W20451838122019 @default.
- W2045183812 crossrefType "proceedings-article" @default.
- W2045183812 hasAuthorship W2045183812A5054900679 @default.
- W2045183812 hasAuthorship W2045183812A5058073627 @default.
- W2045183812 hasAuthorship W2045183812A5059222136 @default.
- W2045183812 hasAuthorship W2045183812A5065452238 @default.
- W2045183812 hasAuthorship W2045183812A5079594267 @default.
- W2045183812 hasAuthorship W2045183812A5085347958 @default.
- W2045183812 hasConcept C113775141 @default.
- W2045183812 hasConcept C119599485 @default.
- W2045183812 hasConcept C119857082 @default.
- W2045183812 hasConcept C124101348 @default.
- W2045183812 hasConcept C127413603 @default.
- W2045183812 hasConcept C147168706 @default.
- W2045183812 hasConcept C150072547 @default.
- W2045183812 hasConcept C154945302 @default.
- W2045183812 hasConcept C173608175 @default.
- W2045183812 hasConcept C2742236 @default.
- W2045183812 hasConcept C41008148 @default.
- W2045183812 hasConcept C50644808 @default.
- W2045183812 hasConcept C75684735 @default.
- W2045183812 hasConcept C79158427 @default.
- W2045183812 hasConceptScore W2045183812C113775141 @default.
- W2045183812 hasConceptScore W2045183812C119599485 @default.
- W2045183812 hasConceptScore W2045183812C119857082 @default.
- W2045183812 hasConceptScore W2045183812C124101348 @default.
- W2045183812 hasConceptScore W2045183812C127413603 @default.
- W2045183812 hasConceptScore W2045183812C147168706 @default.
- W2045183812 hasConceptScore W2045183812C150072547 @default.
- W2045183812 hasConceptScore W2045183812C154945302 @default.
- W2045183812 hasConceptScore W2045183812C173608175 @default.
- W2045183812 hasConceptScore W2045183812C2742236 @default.
- W2045183812 hasConceptScore W2045183812C41008148 @default.
- W2045183812 hasConceptScore W2045183812C50644808 @default.
- W2045183812 hasConceptScore W2045183812C75684735 @default.
- W2045183812 hasConceptScore W2045183812C79158427 @default.
- W2045183812 hasLocation W20451838121 @default.
- W2045183812 hasOpenAccess W2045183812 @default.
- W2045183812 hasPrimaryLocation W20451838121 @default.
- W2045183812 hasRelatedWork W130770469 @default.
- W2045183812 hasRelatedWork W1998917233 @default.
- W2045183812 hasRelatedWork W2027663497 @default.
- W2045183812 hasRelatedWork W2048266589 @default.
- W2045183812 hasRelatedWork W2080451019 @default.
- W2045183812 hasRelatedWork W2091533027 @default.
- W2045183812 hasRelatedWork W2160528526 @default.
- W2045183812 hasRelatedWork W2173213060 @default.
- W2045183812 hasRelatedWork W263472237 @default.
- W2045183812 hasRelatedWork W2810068957 @default.
- W2045183812 hasRelatedWork W2896666858 @default.
- W2045183812 hasRelatedWork W2920081941 @default.
- W2045183812 hasRelatedWork W2943790419 @default.
- W2045183812 hasRelatedWork W2956083712 @default.
- W2045183812 hasRelatedWork W2963526839 @default.
- W2045183812 hasRelatedWork W3022712343 @default.
- W2045183812 hasRelatedWork W3084389077 @default.
- W2045183812 hasRelatedWork W3113153429 @default.
- W2045183812 hasRelatedWork W3140116317 @default.
- W2045183812 hasRelatedWork W3175523456 @default.
- W2045183812 isParatext "false" @default.
- W2045183812 isRetracted "false" @default.
- W2045183812 magId "2045183812" @default.
- W2045183812 workType "article" @default.