FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4380992026> ?p ?o ?g. }

• W4380992026 endingPage "1349" @default.
• W4380992026 startingPage "1334" @default.
• W4380992026 abstract "This paper proposes a memory-efficient deep neural network (DNN) framework-based symbol level precoding (SLP). We focus on a DNN with realistic finite precision weights and adopt an unsupervised deep learning (DL) based SLP model (SLP-DNet). We apply a stochastic quantization (SQ) technique to obtain its corresponding quantized version called SLP-SQDNet. The proposed scheme offers a scalable performance vs memory trade-off, by quantizing a scalable percentage of the DNN weights, and we explore binary and ternary quantizations. Our results show that while SLP-DNet provides near-optimal performance, its quantized versions through SQ yield ~3.46× and ~2.64× model compression for binary-based and ternary-based SLP-SQDNets, respectively. We also find that our proposals offer ~20× and ~10× computational complexity reductions compared to SLP optimization-based and SLP-DNet, respectively." @default.
• W4380992026 created "2023-06-17" @default.
• W4380992026 creator A5003604062 @default.
• W4380992026 creator A5008047912 @default.
• W4380992026 creator A5030334551 @default.
• W4380992026 date "2023-01-01" @default.
• W4380992026 modified "2023-10-18" @default.
• W4380992026 title "A Memory-Efficient Learning Framework for Symbol Level Precoding With Quantized NN Weights" @default.
• W4380992026 cites W1911476179 @default.
• W4380992026 cites W2012325084 @default.
• W4380992026 cites W2018295654 @default.
• W4380992026 cites W2030278492 @default.
• W4380992026 cites W2042599231 @default.
• W4380992026 cites W2044108662 @default.
• W4380992026 cites W2064722620 @default.
• W4380992026 cites W2072599023 @default.
• W4380992026 cites W2079366178 @default.
• W4380992026 cites W2118699525 @default.
• W4380992026 cites W2151716519 @default.
• W4380992026 cites W2152135092 @default.
• W4380992026 cites W2300242332 @default.
• W4380992026 cites W2337246985 @default.
• W4380992026 cites W2475039053 @default.
• W4380992026 cites W2549620397 @default.
• W4380992026 cites W2582583737 @default.
• W4380992026 cites W2585219350 @default.
• W4380992026 cites W2759684853 @default.
• W4380992026 cites W2771808324 @default.
• W4380992026 cites W2786538903 @default.
• W4380992026 cites W2804075771 @default.
• W4380992026 cites W2811302145 @default.
• W4380992026 cites W2890462754 @default.
• W4380992026 cites W2908498346 @default.
• W4380992026 cites W2919311874 @default.
• W4380992026 cites W2963125010 @default.
• W4380992026 cites W2963363373 @default.
• W4380992026 cites W2963408914 @default.
• W4380992026 cites W2963526839 @default.
• W4380992026 cites W2963992461 @default.
• W4380992026 cites W2981819390 @default.
• W4380992026 cites W2998578058 @default.
• W4380992026 cites W3012555737 @default.
• W4380992026 cites W3041405621 @default.
• W4380992026 cites W3045581394 @default.
• W4380992026 cites W3124935769 @default.
• W4380992026 cites W3154472800 @default.
• W4380992026 cites W4225376901 @default.
• W4380992026 cites W4236362309 @default.
• W4380992026 cites W2736356706 @default.
• W4380992026 doi "https://doi.org/10.1109/ojcoms.2023.3285790" @default.
• W4380992026 hasPublicationYear "2023" @default.
• W4380992026 type Work @default.
• W4380992026 citedByCount "0" @default.
• W4380992026 crossrefType "journal-article" @default.
• W4380992026 hasAuthorship W4380992026A5003604062 @default.
• W4380992026 hasAuthorship W4380992026A5008047912 @default.
• W4380992026 hasAuthorship W4380992026A5030334551 @default.
• W4380992026 hasBestOaLocation W43809920261 @default.
• W4380992026 hasConcept C108583219 @default.
• W4380992026 hasConcept C11413529 @default.
• W4380992026 hasConcept C120665830 @default.
• W4380992026 hasConcept C121332964 @default.
• W4380992026 hasConcept C127162648 @default.
• W4380992026 hasConcept C134400042 @default.
• W4380992026 hasConcept C153180895 @default.
• W4380992026 hasConcept C154945302 @default.
• W4380992026 hasConcept C160562895 @default.
• W4380992026 hasConcept C192209626 @default.
• W4380992026 hasConcept C199360897 @default.
• W4380992026 hasConcept C207987634 @default.
• W4380992026 hasConcept C28855332 @default.
• W4380992026 hasConcept C31258907 @default.
• W4380992026 hasConcept C33923547 @default.
• W4380992026 hasConcept C41008148 @default.
• W4380992026 hasConcept C48044578 @default.
• W4380992026 hasConcept C48372109 @default.
• W4380992026 hasConcept C50644808 @default.
• W4380992026 hasConcept C64452783 @default.
• W4380992026 hasConcept C77088390 @default.
• W4380992026 hasConcept C80444323 @default.
• W4380992026 hasConcept C94375191 @default.
• W4380992026 hasConceptScore W4380992026C108583219 @default.
• W4380992026 hasConceptScore W4380992026C11413529 @default.
• W4380992026 hasConceptScore W4380992026C120665830 @default.
• W4380992026 hasConceptScore W4380992026C121332964 @default.
• W4380992026 hasConceptScore W4380992026C127162648 @default.
• W4380992026 hasConceptScore W4380992026C134400042 @default.
• W4380992026 hasConceptScore W4380992026C153180895 @default.
• W4380992026 hasConceptScore W4380992026C154945302 @default.
• W4380992026 hasConceptScore W4380992026C160562895 @default.
• W4380992026 hasConceptScore W4380992026C192209626 @default.
• W4380992026 hasConceptScore W4380992026C199360897 @default.
• W4380992026 hasConceptScore W4380992026C207987634 @default.
• W4380992026 hasConceptScore W4380992026C28855332 @default.
• W4380992026 hasConceptScore W4380992026C31258907 @default.
• W4380992026 hasConceptScore W4380992026C33923547 @default.
• W4380992026 hasConceptScore W4380992026C41008148 @default.
• W4380992026 hasConceptScore W4380992026C48044578 @default.

• next