FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2965851570> ?p ?o ?g. }

• W2965851570 abstract "Despite their outstanding success in solving complex computer vision problems, Deep Neural Networks (DNNs) still require high-performance hardware for real-time inference. Therefore they are not applicable to low-cost embedded hardware, where memory resources, computational performance and power consumption are restricted. Furthermore, current approaches of fitting neural networks to embedded hardware are time consuming, inducing slow development cycles. To address these drawbacks and satisfy the demands of embedded hardware, this paper proposes a computationally efficient magnitude-based pruning scheme, based on a half-interval search, combined with effective weight sharing, fixed-point quantization, and lossless compression. The proposed solution can be utilized to generate an optimized model, either with respect to memory demand or execution time. For instance, the memory demand of LeNet is compressed about 385×. VGG16 is pruned by about 14.5×, whilst its computational costs are reduced by about 1.6× for a CPU-based application and 4.8× for an FPGA one." @default.
• W2965851570 created "2019-08-13" @default.
• W2965851570 creator A5005732789 @default.
• W2965851570 creator A5034106438 @default.
• W2965851570 creator A5047063939 @default.
• W2965851570 date "2019-05-01" @default.
• W2965851570 modified "2023-10-14" @default.
• W2965851570 title "Resource-Aware Optimization of DNNs for Embedded Applications" @default.
• W2965851570 cites W104184427 @default.
• W2965851570 cites W1570197553 @default.
• W2965851570 cites W1686810756 @default.
• W2965851570 cites W171063220 @default.
• W2965851570 cites W1903029394 @default.
• W2965851570 cites W1968874483 @default.
• W2965851570 cites W1980287119 @default.
• W2965851570 cites W1988720110 @default.
• W2965851570 cites W1999085092 @default.
• W2965851570 cites W2060108852 @default.
• W2965851570 cites W2097117768 @default.
• W2965851570 cites W2107878631 @default.
• W2965851570 cites W2112796928 @default.
• W2965851570 cites W2114766824 @default.
• W2965851570 cites W2163605009 @default.
• W2965851570 cites W2279098554 @default.
• W2965851570 cites W2285660444 @default.
• W2965851570 cites W2286365479 @default.
• W2965851570 cites W2419597278 @default.
• W2965851570 cites W2570343428 @default.
• W2965851570 cites W2605736949 @default.
• W2965851570 cites W2619096655 @default.
• W2965851570 cites W2619890685 @default.
• W2965851570 cites W2657126969 @default.
• W2965851570 cites W2791183331 @default.
• W2965851570 cites W2886851211 @default.
• W2965851570 cites W2962861284 @default.
• W2965851570 cites W2963069632 @default.
• W2965851570 cites W2963374099 @default.
• W2965851570 cites W2963452728 @default.
• W2965851570 cites W2963674932 @default.
• W2965851570 cites W2963816728 @default.
• W2965851570 cites W2963981420 @default.
• W2965851570 cites W2964121744 @default.
• W2965851570 cites W2964228333 @default.
• W2965851570 cites W2964299589 @default.
• W2965851570 cites W3106250896 @default.
• W2965851570 cites W587794757 @default.
• W2965851570 doi "https://doi.org/10.1109/crv.2019.00011" @default.
• W2965851570 hasPublicationYear "2019" @default.
• W2965851570 type Work @default.
• W2965851570 sameAs 2965851570 @default.
• W2965851570 citedByCount "4" @default.
• W2965851570 countsByYear W29658515702020 @default.
• W2965851570 crossrefType "proceedings-article" @default.
• W2965851570 hasAuthorship W2965851570A5005732789 @default.
• W2965851570 hasAuthorship W2965851570A5034106438 @default.
• W2965851570 hasAuthorship W2965851570A5047063939 @default.
• W2965851570 hasConcept C108010975 @default.
• W2965851570 hasConcept C113775141 @default.
• W2965851570 hasConcept C11413529 @default.
• W2965851570 hasConcept C149635348 @default.
• W2965851570 hasConcept C154945302 @default.
• W2965851570 hasConcept C173608175 @default.
• W2965851570 hasConcept C2776214188 @default.
• W2965851570 hasConcept C28855332 @default.
• W2965851570 hasConcept C41008148 @default.
• W2965851570 hasConcept C42935608 @default.
• W2965851570 hasConcept C50644808 @default.
• W2965851570 hasConcept C6557445 @default.
• W2965851570 hasConcept C78548338 @default.
• W2965851570 hasConcept C81081738 @default.
• W2965851570 hasConcept C86803240 @default.
• W2965851570 hasConceptScore W2965851570C108010975 @default.
• W2965851570 hasConceptScore W2965851570C113775141 @default.
• W2965851570 hasConceptScore W2965851570C11413529 @default.
• W2965851570 hasConceptScore W2965851570C149635348 @default.
• W2965851570 hasConceptScore W2965851570C154945302 @default.
• W2965851570 hasConceptScore W2965851570C173608175 @default.
• W2965851570 hasConceptScore W2965851570C2776214188 @default.
• W2965851570 hasConceptScore W2965851570C28855332 @default.
• W2965851570 hasConceptScore W2965851570C41008148 @default.
• W2965851570 hasConceptScore W2965851570C42935608 @default.
• W2965851570 hasConceptScore W2965851570C50644808 @default.
• W2965851570 hasConceptScore W2965851570C6557445 @default.
• W2965851570 hasConceptScore W2965851570C78548338 @default.
• W2965851570 hasConceptScore W2965851570C81081738 @default.
• W2965851570 hasConceptScore W2965851570C86803240 @default.
• W2965851570 hasLocation W29658515701 @default.
• W2965851570 hasOpenAccess W2965851570 @default.
• W2965851570 hasPrimaryLocation W29658515701 @default.
• W2965851570 hasRelatedWork W2784596704 @default.
• W2965851570 hasRelatedWork W2791845808 @default.
• W2965851570 hasRelatedWork W2897655610 @default.
• W2965851570 hasRelatedWork W2900694899 @default.
• W2965851570 hasRelatedWork W2903990228 @default.
• W2965851570 hasRelatedWork W2907970550 @default.
• W2965851570 hasRelatedWork W2918653705 @default.
• W2965851570 hasRelatedWork W2960477732 @default.
• W2965851570 hasRelatedWork W2962697884 @default.
• W2965851570 hasRelatedWork W2976077444 @default.
• W2965851570 hasRelatedWork W2982479999 @default.

• next