FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2896611294> ?p ?o ?g. }

• W2896611294 abstract "Deep convolutional neural networks (CNNs) have shown state-of-the-art accuracy for various computer vision and speech tasks. However, CNNs are computation-intensive and energy-inefficient which are difficult to be deployed in real-time systems. Event-driven Spiking Neural Networks (SNNs) are extremely power efficient, which provides an alternative for ultra-low power applications. But effective training methods for SNN are still lacking. Due to its spatio-temporal feature of SNN, conventional training method for CNN can not be employed in SNN. To address this problem, some researchers proposed to convert the corresponding weights of trained CNNs into the synapse weights of SNNs (CNNs-SNNs). Nevertheless, limited by the [0, 1] constraints on the SNN neuron outputs, the accuracy of the converted SNNs is impaired. Besides, as the SNN network becomes deeper, the convergence speed of SNN inference are unacceptably slow. In this work, we proposed an innovative deep multi-strength SNN (M-SNN) structure which relaxes the restriction of the neuron output spike strength while the event-driven feature for low-power implementations is maintained. Using this architecture, large scale SNN can be converted from CNN with comparable accuracy and fast inference speed. The evaluation results show 3.7 × convergence speedup. Moreover, with multi-strength spike, aggressive pruning strategies can be applied to reduce the computational operations by almost 85% while maintaining the same accuracy." @default.
• W2896611294 created "2018-10-26" @default.
• W2896611294 creator A5000050947 @default.
• W2896611294 creator A5002976537 @default.
• W2896611294 creator A5028952508 @default.
• W2896611294 creator A5029924052 @default.
• W2896611294 creator A5031076543 @default.
• W2896611294 creator A5032326710 @default.
• W2896611294 date "2018-07-01" @default.
• W2896611294 modified "2023-10-17" @default.
• W2896611294 title "Fast and Efficient Deep Sparse Multi-Strength Spiking Neural Networks with Dynamic Pruning" @default.
• W2896611294 cites W1645800954 @default.
• W2896611294 cites W2008008156 @default.
• W2896611294 cites W2020676607 @default.
• W2896611294 cites W2107433900 @default.
• W2896611294 cites W2112408199 @default.
• W2896611294 cites W2116360511 @default.
• W2896611294 cites W2138913040 @default.
• W2896611294 cites W2145889472 @default.
• W2896611294 cites W2162827630 @default.
• W2896611294 cites W2165396124 @default.
• W2896611294 cites W2165639766 @default.
• W2896611294 cites W2170968634 @default.
• W2896611294 cites W2276486856 @default.
• W2896611294 cites W2285660444 @default.
• W2896611294 cites W2314470091 @default.
• W2896611294 cites W2513853720 @default.
• W2896611294 cites W2569813014 @default.
• W2896611294 cites W2594492285 @default.
• W2896611294 cites W2625457103 @default.
• W2896611294 cites W2657126969 @default.
• W2896611294 cites W2742439472 @default.
• W2896611294 cites W2775079417 @default.
• W2896611294 doi "https://doi.org/10.1109/ijcnn.2018.8489339" @default.
• W2896611294 hasPublicationYear "2018" @default.
• W2896611294 type Work @default.
• W2896611294 sameAs 2896611294 @default.
• W2896611294 citedByCount "15" @default.
• W2896611294 countsByYear W28966112942020 @default.
• W2896611294 countsByYear W28966112942021 @default.
• W2896611294 countsByYear W28966112942022 @default.
• W2896611294 countsByYear W28966112942023 @default.
• W2896611294 crossrefType "proceedings-article" @default.
• W2896611294 hasAuthorship W2896611294A5000050947 @default.
• W2896611294 hasAuthorship W2896611294A5002976537 @default.
• W2896611294 hasAuthorship W2896611294A5028952508 @default.
• W2896611294 hasAuthorship W2896611294A5029924052 @default.
• W2896611294 hasAuthorship W2896611294A5031076543 @default.
• W2896611294 hasAuthorship W2896611294A5032326710 @default.
• W2896611294 hasConcept C108010975 @default.
• W2896611294 hasConcept C115903868 @default.
• W2896611294 hasConcept C11731999 @default.
• W2896611294 hasConcept C138885662 @default.
• W2896611294 hasConcept C153180895 @default.
• W2896611294 hasConcept C154945302 @default.
• W2896611294 hasConcept C162324750 @default.
• W2896611294 hasConcept C173608175 @default.
• W2896611294 hasConcept C2776214188 @default.
• W2896611294 hasConcept C2776401178 @default.
• W2896611294 hasConcept C2777303404 @default.
• W2896611294 hasConcept C2781390188 @default.
• W2896611294 hasConcept C41008148 @default.
• W2896611294 hasConcept C41895202 @default.
• W2896611294 hasConcept C50522688 @default.
• W2896611294 hasConcept C50644808 @default.
• W2896611294 hasConcept C6557445 @default.
• W2896611294 hasConcept C68339613 @default.
• W2896611294 hasConcept C81363708 @default.
• W2896611294 hasConcept C86803240 @default.
• W2896611294 hasConceptScore W2896611294C108010975 @default.
• W2896611294 hasConceptScore W2896611294C115903868 @default.
• W2896611294 hasConceptScore W2896611294C11731999 @default.
• W2896611294 hasConceptScore W2896611294C138885662 @default.
• W2896611294 hasConceptScore W2896611294C153180895 @default.
• W2896611294 hasConceptScore W2896611294C154945302 @default.
• W2896611294 hasConceptScore W2896611294C162324750 @default.
• W2896611294 hasConceptScore W2896611294C173608175 @default.
• W2896611294 hasConceptScore W2896611294C2776214188 @default.
• W2896611294 hasConceptScore W2896611294C2776401178 @default.
• W2896611294 hasConceptScore W2896611294C2777303404 @default.
• W2896611294 hasConceptScore W2896611294C2781390188 @default.
• W2896611294 hasConceptScore W2896611294C41008148 @default.
• W2896611294 hasConceptScore W2896611294C41895202 @default.
• W2896611294 hasConceptScore W2896611294C50522688 @default.
• W2896611294 hasConceptScore W2896611294C50644808 @default.
• W2896611294 hasConceptScore W2896611294C6557445 @default.
• W2896611294 hasConceptScore W2896611294C68339613 @default.
• W2896611294 hasConceptScore W2896611294C81363708 @default.
• W2896611294 hasConceptScore W2896611294C86803240 @default.
• W2896611294 hasLocation W28966112941 @default.
• W2896611294 hasOpenAccess W2896611294 @default.
• W2896611294 hasPrimaryLocation W28966112941 @default.
• W2896611294 hasRelatedWork W2765989371 @default.
• W2896611294 hasRelatedWork W2767651786 @default.
• W2896611294 hasRelatedWork W2788292821 @default.
• W2896611294 hasRelatedWork W2899244816 @default.
• W2896611294 hasRelatedWork W2912288872 @default.
• W2896611294 hasRelatedWork W3207072508 @default.
• W2896611294 hasRelatedWork W4286251925 @default.
• W2896611294 hasRelatedWork W4312358390 @default.

• next