FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3035397558> ?p ?o ?g. }

• W3035397558 abstract "This paper presents a novel model-driven deep learning (DL) architecture, called TurboNet, for turbo decoding that integrates DL into the traditional max-log-maximum a posteriori (MAP) algorithm. The TurboNet inherits the superiority of the max-log-MAP algorithm and DL tools and thus presents excellent error-correction capability with low training cost. To design the TurboNet, the original iterative structure is unfolded as deep neural network (DNN) decoding units, where trainable weights are introduced to the max-log-MAP algorithm and optimized through supervised learning. To efficiently train the TurboNet, a loss function is carefully designed to prevent tricky gradient vanishing issue. To further reduce the computational complexity and training cost of the TurboNet, we can prune it into TurboNet+. Compared with the existing black-box DL approaches, the TurboNet+ has considerable advantage in computational complexity and is conducive to significantly reducing the decoding overhead. Furthermore, we also present a simple training strategy to address the overfitting issue, which enable efficient training of the proposed TurboNet+. Simulation results demonstrate TurboNet+'s superiority in error-correction ability, signal-to-noise ratio generalization, and computational overhead. In addition, an experimental system is established for an over-the-air (OTA) test with the help of a 5G rapid prototyping system and demonstrates TurboNet's strong learning ability and great robustness to various scenarios." @default.
• W3035397558 created "2020-06-19" @default.
• W3035397558 creator A5005367960 @default.
• W3035397558 creator A5009109404 @default.
• W3035397558 creator A5013079905 @default.
• W3035397558 creator A5024436944 @default.
• W3035397558 creator A5039289964 @default.
• W3035397558 date "2020-06-15" @default.
• W3035397558 modified "2023-09-27" @default.
• W3035397558 title "Model-Driven DNN Decoder for Turbo Codes: Design, Simulation and Experimental Results" @default.
• W3035397558 cites W1562979145 @default.
• W3035397558 cites W1970330710 @default.
• W3035397558 cites W2004229705 @default.
• W3035397558 cites W2083774980 @default.
• W3035397558 cites W2088719955 @default.
• W3035397558 cites W2106509114 @default.
• W3035397558 cites W2118263817 @default.
• W3035397558 cites W2127918465 @default.
• W3035397558 cites W2128765501 @default.
• W3035397558 cites W2148575324 @default.
• W3035397558 cites W2150498905 @default.
• W3035397558 cites W2167984742 @default.
• W3035397558 cites W2206295654 @default.
• W3035397558 cites W2584943905 @default.
• W3035397558 cites W2666368276 @default.
• W3035397558 cites W2734408173 @default.
• W3035397558 cites W2736068844 @default.
• W3035397558 cites W2773170971 @default.
• W3035397558 cites W2886124254 @default.
• W3035397558 cites W2886374543 @default.
• W3035397558 cites W2897042325 @default.
• W3035397558 cites W2921742237 @default.
• W3035397558 cites W2963145597 @default.
• W3035397558 cites W2963190722 @default.
• W3035397558 cites W2963374765 @default.
• W3035397558 cites W2963408536 @default.
• W3035397558 cites W2963889719 @default.
• W3035397558 cites W2964121744 @default.
• W3035397558 cites W2964175260 @default.
• W3035397558 cites W2964231443 @default.
• W3035397558 cites W2966443637 @default.
• W3035397558 cites W2971351707 @default.
• W3035397558 cites W2987657883 @default.
• W3035397558 cites W3005526854 @default.
• W3035397558 cites W3008026851 @default.
• W3035397558 cites W3100636095 @default.
• W3035397558 cites W3152750074 @default.
• W3035397558 cites W1980073965 @default.
• W3035397558 doi "https://doi.org/10.48550/arxiv.2006.08896" @default.
• W3035397558 hasPublicationYear "2020" @default.
• W3035397558 type Work @default.
• W3035397558 sameAs 3035397558 @default.
• W3035397558 citedByCount "0" @default.
• W3035397558 crossrefType "posted-content" @default.
• W3035397558 hasAuthorship W3035397558A5005367960 @default.
• W3035397558 hasAuthorship W3035397558A5009109404 @default.
• W3035397558 hasAuthorship W3035397558A5013079905 @default.
• W3035397558 hasAuthorship W3035397558A5024436944 @default.
• W3035397558 hasAuthorship W3035397558A5039289964 @default.
• W3035397558 hasBestOaLocation W30353975581 @default.
• W3035397558 hasConcept C104317684 @default.
• W3035397558 hasConcept C105795698 @default.
• W3035397558 hasConcept C108583219 @default.
• W3035397558 hasConcept C111919701 @default.
• W3035397558 hasConcept C113775141 @default.
• W3035397558 hasConcept C11413529 @default.
• W3035397558 hasConcept C114504821 @default.
• W3035397558 hasConcept C119857082 @default.
• W3035397558 hasConcept C154945302 @default.
• W3035397558 hasConcept C179799912 @default.
• W3035397558 hasConcept C185592680 @default.
• W3035397558 hasConcept C22019652 @default.
• W3035397558 hasConcept C2779960059 @default.
• W3035397558 hasConcept C33923547 @default.
• W3035397558 hasConcept C41008148 @default.
• W3035397558 hasConcept C49781872 @default.
• W3035397558 hasConcept C50644808 @default.
• W3035397558 hasConcept C55493867 @default.
• W3035397558 hasConcept C57273362 @default.
• W3035397558 hasConcept C63479239 @default.
• W3035397558 hasConcept C9810830 @default.
• W3035397558 hasConceptScore W3035397558C104317684 @default.
• W3035397558 hasConceptScore W3035397558C105795698 @default.
• W3035397558 hasConceptScore W3035397558C108583219 @default.
• W3035397558 hasConceptScore W3035397558C111919701 @default.
• W3035397558 hasConceptScore W3035397558C113775141 @default.
• W3035397558 hasConceptScore W3035397558C11413529 @default.
• W3035397558 hasConceptScore W3035397558C114504821 @default.
• W3035397558 hasConceptScore W3035397558C119857082 @default.
• W3035397558 hasConceptScore W3035397558C154945302 @default.
• W3035397558 hasConceptScore W3035397558C179799912 @default.
• W3035397558 hasConceptScore W3035397558C185592680 @default.
• W3035397558 hasConceptScore W3035397558C22019652 @default.
• W3035397558 hasConceptScore W3035397558C2779960059 @default.
• W3035397558 hasConceptScore W3035397558C33923547 @default.
• W3035397558 hasConceptScore W3035397558C41008148 @default.
• W3035397558 hasConceptScore W3035397558C49781872 @default.
• W3035397558 hasConceptScore W3035397558C50644808 @default.
• W3035397558 hasConceptScore W3035397558C55493867 @default.
• W3035397558 hasConceptScore W3035397558C57273362 @default.

• next