FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3123290820> ?p ?o ?g. }

• W3123290820 endingPage "39" @default.
• W3123290820 startingPage "1" @default.
• W3123290820 abstract "Deep neural networks have proven to be particularly effective in visual and audio recognition tasks. Existing models tend to be computationally expensive and memory intensive, however, and so methods for hardware-oriented approximation have become a hot topic. Research has shown that custom hardware-based neural network accelerators can surpass their general-purpose processor equivalents in terms of both throughput and energy efficiency. Application-tailored accelerators, when co-designed with approximation-based network training methods, transform large, dense, and computationally expensive networks into small, sparse, and hardware-efficient alternatives, increasing the feasibility of network deployment. In this article, we provide a comprehensive evaluation of approximation methods for high-performance network inference along with in-depth discussion of their effectiveness for custom hardware implementation. We also include proposals for future research based on a thorough analysis of current trends. This article represents the first survey providing detailed comparisons of custom hardware accelerators featuring approximation for both convolutional and recurrent neural networks, through which we hope to inspire exciting new developments in the field." @default.
• W3123290820 created "2021-02-01" @default.
• W3123290820 creator A5013225839 @default.
• W3123290820 creator A5023451003 @default.
• W3123290820 creator A5029829952 @default.
• W3123290820 creator A5056354430 @default.
• W3123290820 creator A5056411319 @default.
• W3123290820 creator A5057940557 @default.
• W3123290820 creator A5080658190 @default.
• W3123290820 creator A5091532722 @default.
• W3123290820 date "2020-03-31" @default.
• W3123290820 modified "2023-09-30" @default.
• W3123290820 title "Deep Neural Network Approximation for Custom Hardware" @default.
• W3123290820 cites W1492347181 @default.
• W3123290820 cites W1588915715 @default.
• W3123290820 cites W1919191429 @default.
• W3123290820 cites W1996901117 @default.
• W3123290820 cites W2013188870 @default.
• W3123290820 cites W2016053056 @default.
• W3123290820 cites W2048266589 @default.
• W3123290820 cites W2049009664 @default.
• W3123290820 cites W2091449379 @default.
• W3123290820 cites W2106033855 @default.
• W3123290820 cites W2119112357 @default.
• W3123290820 cites W2124509324 @default.
• W3123290820 cites W2125203716 @default.
• W3123290820 cites W2128853364 @default.
• W3123290820 cites W2152332944 @default.
• W3123290820 cites W2156297475 @default.
• W3123290820 cites W2171319130 @default.
• W3123290820 cites W2233116163 @default.
• W3123290820 cites W2276486856 @default.
• W3123290820 cites W2289252105 @default.
• W3123290820 cites W2300242332 @default.
• W3123290820 cites W2488255893 @default.
• W3123290820 cites W2518660313 @default.
• W3123290820 cites W2520083297 @default.
• W3123290820 cites W2520760693 @default.
• W3123290820 cites W2541839172 @default.
• W3123290820 cites W2542189141 @default.
• W3123290820 cites W2554302513 @default.
• W3123290820 cites W2562773490 @default.
• W3123290820 cites W2563587242 @default.
• W3123290820 cites W2583383421 @default.
• W3123290820 cites W2584311934 @default.
• W3123290820 cites W2585560244 @default.
• W3123290820 cites W2585720638 @default.
• W3123290820 cites W2586654419 @default.
• W3123290820 cites W2588448445 @default.
• W3123290820 cites W2593221942 @default.
• W3123290820 cites W2606722458 @default.
• W3123290820 cites W2625592091 @default.
• W3123290820 cites W2719597717 @default.
• W3123290820 cites W2725615981 @default.
• W3123290820 cites W2730834423 @default.
• W3123290820 cites W2733902982 @default.
• W3123290820 cites W2762597430 @default.
• W3123290820 cites W2762910930 @default.
• W3123290820 cites W2768797272 @default.
• W3123290820 cites W2783538964 @default.
• W3123290820 cites W2788007484 @default.
• W3123290820 cites W2788014245 @default.
• W3123290820 cites W2788838111 @default.
• W3123290820 cites W2789246071 @default.
• W3123290820 cites W2789683730 @default.
• W3123290820 cites W2792742540 @default.
• W3123290820 cites W2793471971 @default.
• W3123290820 cites W2803431233 @default.
• W3123290820 cites W2888727064 @default.
• W3123290820 cites W2892054964 @default.
• W3123290820 cites W2903735800 @default.
• W3123290820 cites W2950656546 @default.
• W3123290820 cites W2962735857 @default.
• W3123290820 cites W2962820060 @default.
• W3123290820 cites W2962851801 @default.
• W3123290820 cites W2962861284 @default.
• W3123290820 cites W2963363373 @default.
• W3123290820 cites W2963367920 @default.
• W3123290820 cites W2963396654 @default.
• W3123290820 cites W2963427045 @default.
• W3123290820 cites W2963526839 @default.
• W3123290820 cites W2963893493 @default.
• W3123290820 cites W2964008850 @default.
• W3123290820 cites W2997106510 @default.
• W3123290820 cites W3102169921 @default.
• W3123290820 cites W3104393472 @default.
• W3123290820 cites W4206196235 @default.
• W3123290820 cites W4245199738 @default.
• W3123290820 cites W4251575795 @default.
• W3123290820 cites W566555209 @default.
• W3123290820 hasPublicationYear "2020" @default.
• W3123290820 type Work @default.
• W3123290820 sameAs 3123290820 @default.
• W3123290820 citedByCount "24" @default.
• W3123290820 countsByYear W31232908202019 @default.
• W3123290820 countsByYear W31232908202020 @default.
• W3123290820 countsByYear W31232908202021 @default.
• W3123290820 crossrefType "journal-article" @default.

• next