Matches in SemOpenAlex for { <https://semopenalex.org/work/W2771127423> ?p ?o ?g. }
Showing items 1 to 95 of
95
with 100 items per page.
- W2771127423 abstract "Modern deep learning enabled artificial neural networks, such as Deep Neural Network (DNN) and Convolutional Neural Network (CNN), have achieved a series of breaking records on a broad spectrum of recognition applications. However, the enormous computation and storage requirements associated with such deep and complex neural network models greatly challenge their implementations on resource-limited platforms. Time-based spiking neural network has recently emerged as a promising solution in Neuromorphic Computing System designs for achieving remarkable computing and power efficiency within a single chip. However, the relevant research activities have been narrowly concentrated on the biological plausibility and theoretical learning approaches, causing inefficient neural processing and impracticable multilayer extension thus significantly limitations on speed and accuracy when handling the realistic cognitive tasks. In this work, a practical multilayer time-based spiking neuromorphic architecture, namely “MT-Spike”, is developed to fill this gap. With the proposed practical time-coding scheme, average delay response model, temporal error backpropagation algorithm and heuristic loss function, “MT-Spike” achieves more efficient neural processing through flexible neural model size reduction while offering very competitive classification accuracy for realistic recognition tasks. Simulation results well validate that the algorithmic power of deep multilayer learning can be seamlessly merged with the efficiency of time-based spiking neuromorphic architecture, demonstrating great potentials of “MT-Spike” in resource and power constrained embedded platforms." @default.
- W2771127423 created "2017-12-22" @default.
- W2771127423 creator A5003718473 @default.
- W2771127423 creator A5017464942 @default.
- W2771127423 creator A5018684814 @default.
- W2771127423 creator A5021568197 @default.
- W2771127423 creator A5067226050 @default.
- W2771127423 creator A5076966605 @default.
- W2771127423 date "2017-11-01" @default.
- W2771127423 modified "2023-10-16" @default.
- W2771127423 title "MT-spike: A multilayer time-based spiking neuromorphic architecture with temporal error backpropagation" @default.
- W2771127423 cites W1530842230 @default.
- W2771127423 cites W1570411240 @default.
- W2771127423 cites W1593079125 @default.
- W2771127423 cites W1604973310 @default.
- W2771127423 cites W1645800954 @default.
- W2771127423 cites W1974983944 @default.
- W2771127423 cites W2020676607 @default.
- W2771127423 cites W2073813638 @default.
- W2771127423 cites W2088192327 @default.
- W2771127423 cites W2098241945 @default.
- W2771127423 cites W2109596721 @default.
- W2771127423 cites W2115831804 @default.
- W2771127423 cites W2131763976 @default.
- W2771127423 cites W2176749394 @default.
- W2771127423 cites W2314470091 @default.
- W2771127423 cites W2431931973 @default.
- W2771127423 cites W2468875367 @default.
- W2771127423 cites W2515417790 @default.
- W2771127423 cites W2554166257 @default.
- W2771127423 cites W2569813014 @default.
- W2771127423 cites W2735894830 @default.
- W2771127423 cites W2766736793 @default.
- W2771127423 cites W2919115771 @default.
- W2771127423 doi "https://doi.org/10.1109/iccad.2017.8203812" @default.
- W2771127423 hasPublicationYear "2017" @default.
- W2771127423 type Work @default.
- W2771127423 sameAs 2771127423 @default.
- W2771127423 citedByCount "19" @default.
- W2771127423 countsByYear W27711274232018 @default.
- W2771127423 countsByYear W27711274232019 @default.
- W2771127423 countsByYear W27711274232020 @default.
- W2771127423 countsByYear W27711274232021 @default.
- W2771127423 countsByYear W27711274232022 @default.
- W2771127423 countsByYear W27711274232023 @default.
- W2771127423 crossrefType "proceedings-article" @default.
- W2771127423 hasAuthorship W2771127423A5003718473 @default.
- W2771127423 hasAuthorship W2771127423A5017464942 @default.
- W2771127423 hasAuthorship W2771127423A5018684814 @default.
- W2771127423 hasAuthorship W2771127423A5021568197 @default.
- W2771127423 hasAuthorship W2771127423A5067226050 @default.
- W2771127423 hasAuthorship W2771127423A5076966605 @default.
- W2771127423 hasBestOaLocation W27711274232 @default.
- W2771127423 hasConcept C108583219 @default.
- W2771127423 hasConcept C115903868 @default.
- W2771127423 hasConcept C11731999 @default.
- W2771127423 hasConcept C119857082 @default.
- W2771127423 hasConcept C151927369 @default.
- W2771127423 hasConcept C153180895 @default.
- W2771127423 hasConcept C154945302 @default.
- W2771127423 hasConcept C155032097 @default.
- W2771127423 hasConcept C2781390188 @default.
- W2771127423 hasConcept C41008148 @default.
- W2771127423 hasConcept C50644808 @default.
- W2771127423 hasConcept C81363708 @default.
- W2771127423 hasConceptScore W2771127423C108583219 @default.
- W2771127423 hasConceptScore W2771127423C115903868 @default.
- W2771127423 hasConceptScore W2771127423C11731999 @default.
- W2771127423 hasConceptScore W2771127423C119857082 @default.
- W2771127423 hasConceptScore W2771127423C151927369 @default.
- W2771127423 hasConceptScore W2771127423C153180895 @default.
- W2771127423 hasConceptScore W2771127423C154945302 @default.
- W2771127423 hasConceptScore W2771127423C155032097 @default.
- W2771127423 hasConceptScore W2771127423C2781390188 @default.
- W2771127423 hasConceptScore W2771127423C41008148 @default.
- W2771127423 hasConceptScore W2771127423C50644808 @default.
- W2771127423 hasConceptScore W2771127423C81363708 @default.
- W2771127423 hasLocation W27711274231 @default.
- W2771127423 hasLocation W27711274232 @default.
- W2771127423 hasOpenAccess W2771127423 @default.
- W2771127423 hasPrimaryLocation W27711274231 @default.
- W2771127423 hasRelatedWork W2947957795 @default.
- W2771127423 hasRelatedWork W2954909726 @default.
- W2771127423 hasRelatedWork W2994834230 @default.
- W2771127423 hasRelatedWork W3156786002 @default.
- W2771127423 hasRelatedWork W3200084004 @default.
- W2771127423 hasRelatedWork W4229069445 @default.
- W2771127423 hasRelatedWork W4287639722 @default.
- W2771127423 hasRelatedWork W4288337556 @default.
- W2771127423 hasRelatedWork W4297889504 @default.
- W2771127423 hasRelatedWork W4320813023 @default.
- W2771127423 isParatext "false" @default.
- W2771127423 isRetracted "false" @default.
- W2771127423 magId "2771127423" @default.
- W2771127423 workType "article" @default.