FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2945250654> ?p ?o ?g. }

• W2945250654 abstract "Recurrent Neural Networks (RNNs) are state-of-the-art models for many machine learning tasks, such as language modeling and machine translation. Executing the inference phase of a RNN directly in edge nodes, rather than in the cloud, would provide benefits in terms of energy consumption, latency and network bandwidth, provided that models can be made efficient enough to run on energy-constrained embedded devices.To this end, we propose an algorithmic optimization for improving the energy efficiency of encoder-decoder RNNs. Our method operates on the Beam Width (BW), i.e. one of the parameters that most influences inference complexity, modulating it depending on the currently processed input based on a metric of the network's confidence.Results on two different machine translation models show that our method is able to reduce the average BW by up to 33%, thus significantly reducing the inference execution time and energy consumption, while maintaining the same translation performance." @default.
• W2945250654 created "2019-05-29" @default.
• W2945250654 creator A5005432629 @default.
• W2945250654 creator A5024891882 @default.
• W2945250654 creator A5030628833 @default.
• W2945250654 creator A5080843266 @default.
• W2945250654 date "2019-05-13" @default.
• W2945250654 modified "2023-09-24" @default.
• W2945250654 title "Dynamic Beam Width Tuning for Energy-Efficient Recurrent Neural Networks" @default.
• W2945250654 cites W2094756095 @default.
• W2945250654 cites W2604319603 @default.
• W2945250654 cites W2788838111 @default.
• W2945250654 cites W2888842187 @default.
• W2945250654 cites W2906043559 @default.
• W2945250654 cites W2963212250 @default.
• W2945250654 cites W3105248137 @default.
• W2945250654 cites W3125484574 @default.
• W2945250654 doi "https://doi.org/10.1145/3299874.3317974" @default.
• W2945250654 hasPublicationYear "2019" @default.
• W2945250654 type Work @default.
• W2945250654 sameAs 2945250654 @default.
• W2945250654 citedByCount "4" @default.
• W2945250654 countsByYear W29452506542020 @default.
• W2945250654 countsByYear W29452506542022 @default.
• W2945250654 crossrefType "proceedings-article" @default.
• W2945250654 hasAuthorship W2945250654A5005432629 @default.
• W2945250654 hasAuthorship W2945250654A5024891882 @default.
• W2945250654 hasAuthorship W2945250654A5030628833 @default.
• W2945250654 hasAuthorship W2945250654A5080843266 @default.
• W2945250654 hasConcept C120665830 @default.
• W2945250654 hasConcept C121332964 @default.
• W2945250654 hasConcept C147168706 @default.
• W2945250654 hasConcept C154945302 @default.
• W2945250654 hasConcept C168834538 @default.
• W2945250654 hasConcept C186370098 @default.
• W2945250654 hasConcept C41008148 @default.
• W2945250654 hasConcept C50644808 @default.
• W2945250654 hasConcept C62520636 @default.
• W2945250654 hasConceptScore W2945250654C120665830 @default.
• W2945250654 hasConceptScore W2945250654C121332964 @default.
• W2945250654 hasConceptScore W2945250654C147168706 @default.
• W2945250654 hasConceptScore W2945250654C154945302 @default.
• W2945250654 hasConceptScore W2945250654C168834538 @default.
• W2945250654 hasConceptScore W2945250654C186370098 @default.
• W2945250654 hasConceptScore W2945250654C41008148 @default.
• W2945250654 hasConceptScore W2945250654C50644808 @default.
• W2945250654 hasConceptScore W2945250654C62520636 @default.
• W2945250654 hasLocation W29452506541 @default.
• W2945250654 hasOpenAccess W2945250654 @default.
• W2945250654 hasPrimaryLocation W29452506541 @default.
• W2945250654 hasRelatedWork W1814702984 @default.
• W2945250654 hasRelatedWork W1999206438 @default.
• W2945250654 hasRelatedWork W2086999410 @default.
• W2945250654 hasRelatedWork W2386387936 @default.
• W2945250654 hasRelatedWork W2726198365 @default.
• W2945250654 hasRelatedWork W2782968911 @default.
• W2945250654 hasRelatedWork W2950022897 @default.
• W2945250654 hasRelatedWork W3045439786 @default.
• W2945250654 hasRelatedWork W4224913944 @default.
• W2945250654 hasRelatedWork W4288081727 @default.
• W2945250654 isParatext "false" @default.
• W2945250654 isRetracted "false" @default.
• W2945250654 magId "2945250654" @default.
• W2945250654 workType "article" @default.