Matches in SemOpenAlex for { <https://semopenalex.org/work/W2588285023> ?p ?o ?g. }
Showing items 1 to 96 of
96
with 100 items per page.
- W2588285023 endingPage "814" @default.
- W2588285023 startingPage "791" @default.
- W2588285023 abstract "Most of the research on deep neural networks so far has been focused on obtaining higher accuracy levels by building increasingly large and deep architectures. Training and evaluating these models is only feasible when large amounts of resources such as processing power and memory are available. Typical applications that could benefit from these models are, however, executed on resource-constrained devices. Mobile devices such as smartphones already use deep learning techniques, but they often have to perform all processing on a remote cloud. We propose a new architecture called a cascading network that is capable of distributing a deep neural network between a local device and the cloud while keeping the required communication network traffic to a minimum. The network begins processing on the constrained device, and only relies on the remote part when the local part does not provide an accurate enough result. The cascading network allows for an early-stopping mechanism during the recall phase of the network. We evaluated our approach in an Internet of Things context where a deep neural network adds intelligence to a large amount of heterogeneous connected devices. This technique enables a whole variety of autonomous systems where sensors, actuators and computing nodes can work together. We show that the cascading architecture allows for a substantial improvement in evaluation speed on constrained devices while the loss in accuracy is kept to a minimum." @default.
- W2588285023 created "2017-02-24" @default.
- W2588285023 creator A5001314520 @default.
- W2588285023 creator A5020261747 @default.
- W2588285023 creator A5026245125 @default.
- W2588285023 creator A5032558375 @default.
- W2588285023 creator A5036700347 @default.
- W2588285023 creator A5061031206 @default.
- W2588285023 creator A5071221406 @default.
- W2588285023 date "2017-02-16" @default.
- W2588285023 modified "2023-09-25" @default.
- W2588285023 title "The cascading neural network: building the Internet of Smart Things" @default.
- W2588285023 cites W1628133262 @default.
- W2588285023 cites W1971901219 @default.
- W2588285023 cites W1980501707 @default.
- W2588285023 cites W1988720110 @default.
- W2588285023 cites W2013011733 @default.
- W2588285023 cites W2076063813 @default.
- W2588285023 cites W2081580037 @default.
- W2588285023 cites W2108598243 @default.
- W2588285023 cites W2112796928 @default.
- W2588285023 cites W2114623221 @default.
- W2588285023 cites W2137983211 @default.
- W2588285023 cites W2163922914 @default.
- W2588285023 cites W2294370754 @default.
- W2588285023 cites W3097096317 @default.
- W2588285023 cites W4231109964 @default.
- W2588285023 cites W4235270414 @default.
- W2588285023 cites W4243928383 @default.
- W2588285023 doi "https://doi.org/10.1007/s10115-017-1029-1" @default.
- W2588285023 hasPublicationYear "2017" @default.
- W2588285023 type Work @default.
- W2588285023 sameAs 2588285023 @default.
- W2588285023 citedByCount "45" @default.
- W2588285023 countsByYear W25882850232017 @default.
- W2588285023 countsByYear W25882850232018 @default.
- W2588285023 countsByYear W25882850232019 @default.
- W2588285023 countsByYear W25882850232020 @default.
- W2588285023 countsByYear W25882850232021 @default.
- W2588285023 countsByYear W25882850232022 @default.
- W2588285023 countsByYear W25882850232023 @default.
- W2588285023 crossrefType "journal-article" @default.
- W2588285023 hasAuthorship W2588285023A5001314520 @default.
- W2588285023 hasAuthorship W2588285023A5020261747 @default.
- W2588285023 hasAuthorship W2588285023A5026245125 @default.
- W2588285023 hasAuthorship W2588285023A5032558375 @default.
- W2588285023 hasAuthorship W2588285023A5036700347 @default.
- W2588285023 hasAuthorship W2588285023A5061031206 @default.
- W2588285023 hasAuthorship W2588285023A5071221406 @default.
- W2588285023 hasBestOaLocation W25882850232 @default.
- W2588285023 hasConcept C108583219 @default.
- W2588285023 hasConcept C111919701 @default.
- W2588285023 hasConcept C120314980 @default.
- W2588285023 hasConcept C151730666 @default.
- W2588285023 hasConcept C154945302 @default.
- W2588285023 hasConcept C193415008 @default.
- W2588285023 hasConcept C2779343474 @default.
- W2588285023 hasConcept C31258907 @default.
- W2588285023 hasConcept C41008148 @default.
- W2588285023 hasConcept C50644808 @default.
- W2588285023 hasConcept C79974875 @default.
- W2588285023 hasConcept C86803240 @default.
- W2588285023 hasConceptScore W2588285023C108583219 @default.
- W2588285023 hasConceptScore W2588285023C111919701 @default.
- W2588285023 hasConceptScore W2588285023C120314980 @default.
- W2588285023 hasConceptScore W2588285023C151730666 @default.
- W2588285023 hasConceptScore W2588285023C154945302 @default.
- W2588285023 hasConceptScore W2588285023C193415008 @default.
- W2588285023 hasConceptScore W2588285023C2779343474 @default.
- W2588285023 hasConceptScore W2588285023C31258907 @default.
- W2588285023 hasConceptScore W2588285023C41008148 @default.
- W2588285023 hasConceptScore W2588285023C50644808 @default.
- W2588285023 hasConceptScore W2588285023C79974875 @default.
- W2588285023 hasConceptScore W2588285023C86803240 @default.
- W2588285023 hasIssue "3" @default.
- W2588285023 hasLocation W25882850231 @default.
- W2588285023 hasLocation W25882850232 @default.
- W2588285023 hasOpenAccess W2588285023 @default.
- W2588285023 hasPrimaryLocation W25882850231 @default.
- W2588285023 hasRelatedWork W2060798312 @default.
- W2588285023 hasRelatedWork W2168831008 @default.
- W2588285023 hasRelatedWork W2383532021 @default.
- W2588285023 hasRelatedWork W2517027266 @default.
- W2588285023 hasRelatedWork W2731899572 @default.
- W2588285023 hasRelatedWork W2939353110 @default.
- W2588285023 hasRelatedWork W3009238340 @default.
- W2588285023 hasRelatedWork W3091976719 @default.
- W2588285023 hasRelatedWork W3215138031 @default.
- W2588285023 hasRelatedWork W4321369474 @default.
- W2588285023 hasVolume "52" @default.
- W2588285023 isParatext "false" @default.
- W2588285023 isRetracted "false" @default.
- W2588285023 magId "2588285023" @default.
- W2588285023 workType "article" @default.