FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2896890100> ?p ?o ?g. }

• W2896890100 endingPage "38" @default.
• W2896890100 startingPage "38" @default.
• W2896890100 abstract "Applications of neural networks have gained significant importance in embedded mobile devices and Internet of Things (IoT) nodes. In particular, convolutional neural networks have emerged as one of the most powerful techniques in computer vision, speech recognition, and AI applications that can improve the mobile user experience. However, satisfying all power and performance requirements of such low power devices is a significant challenge. Recent work has shown that binarizing a neural network can significantly improve the memory requirements of mobile devices at the cost of minor loss in accuracy. This paper proposes MB-CNN, a memristive accelerator for binary convolutional neural networks that perform XNOR convolution in-situ novel 2R memristive data blocks to improve power, performance, and memory requirements of embedded mobile devices. The proposed accelerator achieves at least 13.26 × , 5.91 × , and 3.18 × improvements in the system energy efficiency (computed by energy × delay) over the state-of-the-art software, GPU, and PIM architectures, respectively. The solution architecture which integrates CPU, GPU and MB-CNN outperforms every other configuration in terms of system energy and execution time." @default.
• W2896890100 created "2018-10-26" @default.
• W2896890100 creator A5008878539 @default.
• W2896890100 creator A5071802262 @default.
• W2896890100 creator A5071882119 @default.
• W2896890100 date "2018-10-13" @default.
• W2896890100 modified "2023-09-26" @default.
• W2896890100 title "MB-CNN: Memristive Binary Convolutional Neural Networks for Embedded Mobile Devices" @default.
• W2896890100 cites W1773932593 @default.
• W2896890100 cites W2010202670 @default.
• W2896890100 cites W2013055927 @default.
• W2896890100 cites W2024502754 @default.
• W2896890100 cites W2034876082 @default.
• W2896890100 cites W2060207652 @default.
• W2896890100 cites W2072740080 @default.
• W2896890100 cites W2095076490 @default.
• W2896890100 cites W2109299775 @default.
• W2896890100 cites W2112547256 @default.
• W2896890100 cites W2112796928 @default.
• W2896890100 cites W2117539524 @default.
• W2896890100 cites W2122287325 @default.
• W2896890100 cites W2125700950 @default.
• W2896890100 cites W2136268150 @default.
• W2896890100 cites W2143483829 @default.
• W2896890100 cites W2147800946 @default.
• W2896890100 cites W2162632236 @default.
• W2896890100 cites W2178102281 @default.
• W2896890100 cites W2292040071 @default.
• W2896890100 cites W2338411938 @default.
• W2896890100 cites W2436300686 @default.
• W2896890100 cites W2463902435 @default.
• W2896890100 cites W2543034153 @default.
• W2896890100 cites W2560282050 @default.
• W2896890100 cites W2789927962 @default.
• W2896890100 doi "https://doi.org/10.3390/jlpea8040038" @default.
• W2896890100 hasPublicationYear "2018" @default.
• W2896890100 type Work @default.
• W2896890100 sameAs 2896890100 @default.
• W2896890100 citedByCount "12" @default.
• W2896890100 countsByYear W28968901002018 @default.
• W2896890100 countsByYear W28968901002019 @default.
• W2896890100 countsByYear W28968901002020 @default.
• W2896890100 countsByYear W28968901002021 @default.
• W2896890100 countsByYear W28968901002022 @default.
• W2896890100 countsByYear W28968901002023 @default.
• W2896890100 crossrefType "journal-article" @default.
• W2896890100 hasAuthorship W2896890100A5008878539 @default.
• W2896890100 hasAuthorship W2896890100A5071802262 @default.
• W2896890100 hasAuthorship W2896890100A5071882119 @default.
• W2896890100 hasBestOaLocation W28968901001 @default.
• W2896890100 hasConcept C108583219 @default.
• W2896890100 hasConcept C111919701 @default.
• W2896890100 hasConcept C113775141 @default.
• W2896890100 hasConcept C11413529 @default.
• W2896890100 hasConcept C118524514 @default.
• W2896890100 hasConcept C124296912 @default.
• W2896890100 hasConcept C127413603 @default.
• W2896890100 hasConcept C131017901 @default.
• W2896890100 hasConcept C149635348 @default.
• W2896890100 hasConcept C150072547 @default.
• W2896890100 hasConcept C154945302 @default.
• W2896890100 hasConcept C186967261 @default.
• W2896890100 hasConcept C24326235 @default.
• W2896890100 hasConcept C41008148 @default.
• W2896890100 hasConcept C50644808 @default.
• W2896890100 hasConcept C57684291 @default.
• W2896890100 hasConcept C81363708 @default.
• W2896890100 hasConcept C9390403 @default.
• W2896890100 hasConceptScore W2896890100C108583219 @default.
• W2896890100 hasConceptScore W2896890100C111919701 @default.
• W2896890100 hasConceptScore W2896890100C113775141 @default.
• W2896890100 hasConceptScore W2896890100C11413529 @default.
• W2896890100 hasConceptScore W2896890100C118524514 @default.
• W2896890100 hasConceptScore W2896890100C124296912 @default.
• W2896890100 hasConceptScore W2896890100C127413603 @default.
• W2896890100 hasConceptScore W2896890100C131017901 @default.
• W2896890100 hasConceptScore W2896890100C149635348 @default.
• W2896890100 hasConceptScore W2896890100C150072547 @default.
• W2896890100 hasConceptScore W2896890100C154945302 @default.
• W2896890100 hasConceptScore W2896890100C186967261 @default.
• W2896890100 hasConceptScore W2896890100C24326235 @default.
• W2896890100 hasConceptScore W2896890100C41008148 @default.
• W2896890100 hasConceptScore W2896890100C50644808 @default.
• W2896890100 hasConceptScore W2896890100C57684291 @default.
• W2896890100 hasConceptScore W2896890100C81363708 @default.
• W2896890100 hasConceptScore W2896890100C9390403 @default.
• W2896890100 hasIssue "4" @default.
• W2896890100 hasLocation W28968901001 @default.
• W2896890100 hasLocation W28968901002 @default.
• W2896890100 hasOpenAccess W2896890100 @default.
• W2896890100 hasPrimaryLocation W28968901001 @default.
• W2896890100 hasRelatedWork W2524802307 @default.
• W2896890100 hasRelatedWork W2608484494 @default.
• W2896890100 hasRelatedWork W2734763043 @default.
• W2896890100 hasRelatedWork W2775811337 @default.
• W2896890100 hasRelatedWork W2801463139 @default.
• W2896890100 hasRelatedWork W2882546831 @default.
• W2896890100 hasRelatedWork W2954307240 @default.

• next