FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3007231662> ?p ?o ?g. }

• W3007231662 abstract "The operations used for neural network computation map favorably onto simple analog circuits, which outshine their digital counterparts in terms of compactness and efficiency. Nevertheless, such implementations have been largely supplanted by digital designs, partly because of device mismatch effects due to material and fabrication imperfections. We propose a framework that exploits the power of deep learning to compensate for this mismatch by incorporating the measured device variations as constraints in the neural network training process. This eliminates the need for mismatch minimization strategies and allows circuit complexity and power-consumption to be reduced to a minimum. Our results, based on large-scale simulations as well as a prototype VLSI chip implementation indicate a processing efficiency comparable to current state-of-art digital implementations. This method is suitable for future technology based on nanodevices with large variability, such as memristive arrays." @default.
• W3007231662 created "2020-03-06" @default.
• W3007231662 creator A5035400021 @default.
• W3007231662 creator A5053813559 @default.
• W3007231662 creator A5053821067 @default.
• W3007231662 creator A5060241952 @default.
• W3007231662 creator A5063536196 @default.
• W3007231662 date "2016-06-23" @default.
• W3007231662 modified "2023-09-27" @default.
• W3007231662 title "Precise neural network computation with imprecise analog devices" @default.
• W3007231662 cites W1542981317 @default.
• W3007231662 cites W1546843038 @default.
• W3007231662 cites W1667115661 @default.
• W3007231662 cites W1695065985 @default.
• W3007231662 cites W1821462560 @default.
• W3007231662 cites W1979974160 @default.
• W3007231662 cites W1998385236 @default.
• W3007231662 cites W2008008156 @default.
• W3007231662 cites W2015284628 @default.
• W3007231662 cites W2040429262 @default.
• W3007231662 cites W2040870580 @default.
• W3007231662 cites W2044535169 @default.
• W3007231662 cites W2048266589 @default.
• W3007231662 cites W2049986605 @default.
• W3007231662 cites W2064675550 @default.
• W3007231662 cites W2070167224 @default.
• W3007231662 cites W2101295542 @default.
• W3007231662 cites W2103452702 @default.
• W3007231662 cites W2110033475 @default.
• W3007231662 cites W2111968304 @default.
• W3007231662 cites W2113929681 @default.
• W3007231662 cites W2116353458 @default.
• W3007231662 cites W2125982462 @default.
• W3007231662 cites W2138913040 @default.
• W3007231662 cites W2140823559 @default.
• W3007231662 cites W2141564467 @default.
• W3007231662 cites W2172307690 @default.
• W3007231662 cites W2185491959 @default.
• W3007231662 cites W2286256158 @default.
• W3007231662 cites W2289252105 @default.
• W3007231662 cites W2292733612 @default.
• W3007231662 cites W2320696484 @default.
• W3007231662 cites W2323986115 @default.
• W3007231662 cites W238464747 @default.
• W3007231662 cites W2536505949 @default.
• W3007231662 cites W2759596461 @default.
• W3007231662 cites W2950769435 @default.
• W3007231662 cites W2963114950 @default.
• W3007231662 cites W2964121744 @default.
• W3007231662 cites W2964299589 @default.
• W3007231662 cites W639309485 @default.
• W3007231662 hasPublicationYear "2016" @default.
• W3007231662 type Work @default.
• W3007231662 sameAs 3007231662 @default.
• W3007231662 citedByCount "0" @default.
• W3007231662 crossrefType "posted-content" @default.
• W3007231662 hasAuthorship W3007231662A5035400021 @default.
• W3007231662 hasAuthorship W3007231662A5053813559 @default.
• W3007231662 hasAuthorship W3007231662A5053821067 @default.
• W3007231662 hasAuthorship W3007231662A5060241952 @default.
• W3007231662 hasAuthorship W3007231662A5063536196 @default.
• W3007231662 hasConcept C113775141 @default.
• W3007231662 hasConcept C11413529 @default.
• W3007231662 hasConcept C118524514 @default.
• W3007231662 hasConcept C119599485 @default.
• W3007231662 hasConcept C127413603 @default.
• W3007231662 hasConcept C134146338 @default.
• W3007231662 hasConcept C14580979 @default.
• W3007231662 hasConcept C147764199 @default.
• W3007231662 hasConcept C149635348 @default.
• W3007231662 hasConcept C154945302 @default.
• W3007231662 hasConcept C165696696 @default.
• W3007231662 hasConcept C199360897 @default.
• W3007231662 hasConcept C24326235 @default.
• W3007231662 hasConcept C26713055 @default.
• W3007231662 hasConcept C29074008 @default.
• W3007231662 hasConcept C38652104 @default.
• W3007231662 hasConcept C41008148 @default.
• W3007231662 hasConcept C45374587 @default.
• W3007231662 hasConcept C50644808 @default.
• W3007231662 hasConcept C81843906 @default.
• W3007231662 hasConceptScore W3007231662C113775141 @default.
• W3007231662 hasConceptScore W3007231662C11413529 @default.
• W3007231662 hasConceptScore W3007231662C118524514 @default.
• W3007231662 hasConceptScore W3007231662C119599485 @default.
• W3007231662 hasConceptScore W3007231662C127413603 @default.
• W3007231662 hasConceptScore W3007231662C134146338 @default.
• W3007231662 hasConceptScore W3007231662C14580979 @default.
• W3007231662 hasConceptScore W3007231662C147764199 @default.
• W3007231662 hasConceptScore W3007231662C149635348 @default.
• W3007231662 hasConceptScore W3007231662C154945302 @default.
• W3007231662 hasConceptScore W3007231662C165696696 @default.
• W3007231662 hasConceptScore W3007231662C199360897 @default.
• W3007231662 hasConceptScore W3007231662C24326235 @default.
• W3007231662 hasConceptScore W3007231662C26713055 @default.
• W3007231662 hasConceptScore W3007231662C29074008 @default.
• W3007231662 hasConceptScore W3007231662C38652104 @default.
• W3007231662 hasConceptScore W3007231662C41008148 @default.
• W3007231662 hasConceptScore W3007231662C45374587 @default.
• W3007231662 hasConceptScore W3007231662C50644808 @default.

• next