Matches in SemOpenAlex for { <https://semopenalex.org/work/W2786266960> ?p ?o ?g. }
Showing items 1 to 99 of
99
with 100 items per page.
- W2786266960 abstract "With recent trend of wearable devices and Internet of Things (IoTs), it becomes attractive to develop hardware-based deep convolutional neural networks (DCNNs) for embedded applications, which require low power/energy consumptions and small hardware footprints. Recent works demonstrated that the Stochastic Computing (SC) technique can radically simplify the hardware implementation of arithmetic units and has the potential to satisfy the stringent power requirements in embedded devices. However, in these works, the memory design optimization is neglected for weight storage, which will inevitably result in large hardware cost. Moreover, if conventional volatile SRAM or DRAM cells are utilized for weight storage, the weights need to be re-initialized whenever the DCNN platform is re-started. In order to overcome these limitations, in this work we adopt an emerging non-volatile Domain-Wall Memory (DWM), which can achieve ultra-high density, to replace SRAM for weight storage in SC-based DCNNs. We propose DW-CNN, the first comprehensive design optimization framework of DWM-based weight storage method. We derive the optimal memory type, precision, and organization, as well as whether to store binary or stochastic numbers. We present effective resource sharing scheme for DWM-based weight storage in the convolutional and fully-connected layers of SC-based DCNNs to achieve a desirable balance among area, power (energy) consumption, and application-level accuracy." @default.
- W2786266960 created "2018-02-23" @default.
- W2786266960 creator A5005550142 @default.
- W2786266960 creator A5007300551 @default.
- W2786266960 creator A5016070401 @default.
- W2786266960 creator A5023826377 @default.
- W2786266960 creator A5025596795 @default.
- W2786266960 creator A5051490998 @default.
- W2786266960 creator A5064144989 @default.
- W2786266960 creator A5066534595 @default.
- W2786266960 date "2018-02-03" @default.
- W2786266960 modified "2023-10-18" @default.
- W2786266960 title "An Area and Energy Efficient Design of Domain-Wall Memory-Based Deep Convolutional Neural Networks using Stochastic Computing" @default.
- W2786266960 cites W1527702126 @default.
- W2786266960 cites W1666962919 @default.
- W2786266960 cites W1890351280 @default.
- W2786266960 cites W1981443800 @default.
- W2786266960 cites W2004652177 @default.
- W2786266960 cites W2025295061 @default.
- W2786266960 cites W2033188264 @default.
- W2786266960 cites W2076063813 @default.
- W2786266960 cites W2077496761 @default.
- W2786266960 cites W2094756095 @default.
- W2786266960 cites W2112796928 @default.
- W2786266960 cites W2118572719 @default.
- W2786266960 cites W2130325614 @default.
- W2786266960 cites W2132241724 @default.
- W2786266960 cites W2290548492 @default.
- W2786266960 cites W2299560900 @default.
- W2786266960 cites W2509876617 @default.
- W2786266960 cites W2588598812 @default.
- W2786266960 cites W2588861206 @default.
- W2786266960 cites W2616152995 @default.
- W2786266960 cites W2769269352 @default.
- W2786266960 cites W2919115771 @default.
- W2786266960 cites W2949097947 @default.
- W2786266960 cites W2949168242 @default.
- W2786266960 cites W2952653240 @default.
- W2786266960 cites W2962820060 @default.
- W2786266960 cites W2963147303 @default.
- W2786266960 cites W3104393472 @default.
- W2786266960 doi "https://doi.org/10.48550/arxiv.1802.01016" @default.
- W2786266960 hasPublicationYear "2018" @default.
- W2786266960 type Work @default.
- W2786266960 sameAs 2786266960 @default.
- W2786266960 citedByCount "0" @default.
- W2786266960 crossrefType "posted-content" @default.
- W2786266960 hasAuthorship W2786266960A5005550142 @default.
- W2786266960 hasAuthorship W2786266960A5007300551 @default.
- W2786266960 hasAuthorship W2786266960A5016070401 @default.
- W2786266960 hasAuthorship W2786266960A5023826377 @default.
- W2786266960 hasAuthorship W2786266960A5025596795 @default.
- W2786266960 hasAuthorship W2786266960A5051490998 @default.
- W2786266960 hasAuthorship W2786266960A5064144989 @default.
- W2786266960 hasAuthorship W2786266960A5066534595 @default.
- W2786266960 hasBestOaLocation W27862669601 @default.
- W2786266960 hasConcept C113775141 @default.
- W2786266960 hasConcept C120314980 @default.
- W2786266960 hasConcept C134306372 @default.
- W2786266960 hasConcept C149635348 @default.
- W2786266960 hasConcept C154945302 @default.
- W2786266960 hasConcept C173608175 @default.
- W2786266960 hasConcept C33923547 @default.
- W2786266960 hasConcept C36503486 @default.
- W2786266960 hasConcept C41008148 @default.
- W2786266960 hasConcept C68043766 @default.
- W2786266960 hasConcept C7366592 @default.
- W2786266960 hasConcept C81363708 @default.
- W2786266960 hasConcept C9390403 @default.
- W2786266960 hasConceptScore W2786266960C113775141 @default.
- W2786266960 hasConceptScore W2786266960C120314980 @default.
- W2786266960 hasConceptScore W2786266960C134306372 @default.
- W2786266960 hasConceptScore W2786266960C149635348 @default.
- W2786266960 hasConceptScore W2786266960C154945302 @default.
- W2786266960 hasConceptScore W2786266960C173608175 @default.
- W2786266960 hasConceptScore W2786266960C33923547 @default.
- W2786266960 hasConceptScore W2786266960C36503486 @default.
- W2786266960 hasConceptScore W2786266960C41008148 @default.
- W2786266960 hasConceptScore W2786266960C68043766 @default.
- W2786266960 hasConceptScore W2786266960C7366592 @default.
- W2786266960 hasConceptScore W2786266960C81363708 @default.
- W2786266960 hasConceptScore W2786266960C9390403 @default.
- W2786266960 hasLocation W27862669601 @default.
- W2786266960 hasOpenAccess W2786266960 @default.
- W2786266960 hasPrimaryLocation W27862669601 @default.
- W2786266960 hasRelatedWork W1574438493 @default.
- W2786266960 hasRelatedWork W1677565170 @default.
- W2786266960 hasRelatedWork W1764185321 @default.
- W2786266960 hasRelatedWork W1850654559 @default.
- W2786266960 hasRelatedWork W2122895920 @default.
- W2786266960 hasRelatedWork W2125955295 @default.
- W2786266960 hasRelatedWork W2946152667 @default.
- W2786266960 hasRelatedWork W3114050501 @default.
- W2786266960 hasRelatedWork W4210382982 @default.
- W2786266960 hasRelatedWork W632940705 @default.
- W2786266960 isParatext "false" @default.
- W2786266960 isRetracted "false" @default.
- W2786266960 magId "2786266960" @default.
- W2786266960 workType "article" @default.