Matches in SemOpenAlex for { <https://semopenalex.org/work/W4313430026> ?p ?o ?g. }
- W4313430026 endingPage "880" @default.
- W4313430026 startingPage "870" @default.
- W4313430026 abstract "Memristor-based neuromorphic computing could overcome the limitations of traditional von Neumann computing architectures—in which data are shuffled between separate memory and processing units—and improve the performance of deep neural networks. However, this will require accurate synaptic-like device performance, and memristors typically suffer from poor yield and a limited number of reliable conductance states. Here we report floating-gate memristive synaptic devices that are fabricated in a commercial complementary metal–oxide–semiconductor process. These silicon synapses offer analogue tunability, high endurance, long retention time, predictable cycling degradation, moderate device-to-device variation and high yield. They also provide two orders of magnitude higher energy efficiency for multiply–accumulate operations than graphics processing units. We use two 12 × 8 arrays of memristive devices for the in situ training of a 19 × 8 memristive restricted Boltzmann machine for pattern recognition via a gradient descent algorithm based on contrastive divergence. We then create a memristive deep belief neural network consisting of three memristive restricted Boltzmann machines. We test this system using the modified National Institute of Standards and Technology dataset, demonstrating a recognition accuracy of up to 97.05%. Floating-gate memristive synaptic devices that are fabricated using commercial complementary metal–oxide–semiconductor processes can be used to create energy-efficient restricted Boltzmann machines and deep belief neural networks." @default.
- W4313430026 created "2023-01-06" @default.
- W4313430026 creator A5014138496 @default.
- W4313430026 creator A5018201019 @default.
- W4313430026 creator A5027074781 @default.
- W4313430026 creator A5032249041 @default.
- W4313430026 creator A5035176203 @default.
- W4313430026 creator A5055936327 @default.
- W4313430026 creator A5061181795 @default.
- W4313430026 creator A5082597513 @default.
- W4313430026 creator A5090042508 @default.
- W4313430026 date "2022-12-19" @default.
- W4313430026 modified "2023-10-14" @default.
- W4313430026 title "A memristive deep belief neural network based on silicon synapses" @default.
- W4313430026 cites W1530377216 @default.
- W4313430026 cites W1937359183 @default.
- W4313430026 cites W1982449228 @default.
- W4313430026 cites W1993845689 @default.
- W4313430026 cites W2040429262 @default.
- W4313430026 cites W2047552062 @default.
- W4313430026 cites W2060501200 @default.
- W4313430026 cites W2069164217 @default.
- W4313430026 cites W2094647593 @default.
- W4313430026 cites W2111865441 @default.
- W4313430026 cites W2112796928 @default.
- W4313430026 cites W2115794467 @default.
- W4313430026 cites W2116064496 @default.
- W4313430026 cites W2136922672 @default.
- W4313430026 cites W2155954834 @default.
- W4313430026 cites W2307193480 @default.
- W4313430026 cites W2598219943 @default.
- W4313430026 cites W2613205562 @default.
- W4313430026 cites W2613989746 @default.
- W4313430026 cites W2769049661 @default.
- W4313430026 cites W2778935320 @default.
- W4313430026 cites W2786651150 @default.
- W4313430026 cites W2787759178 @default.
- W4313430026 cites W2796301411 @default.
- W4313430026 cites W2801035805 @default.
- W4313430026 cites W2802755967 @default.
- W4313430026 cites W2803163155 @default.
- W4313430026 cites W2805362231 @default.
- W4313430026 cites W2836219189 @default.
- W4313430026 cites W2883711383 @default.
- W4313430026 cites W2889886075 @default.
- W4313430026 cites W2919115771 @default.
- W4313430026 cites W2922168646 @default.
- W4313430026 cites W2923010225 @default.
- W4313430026 cites W2942216650 @default.
- W4313430026 cites W2960778947 @default.
- W4313430026 cites W2963385418 @default.
- W4313430026 cites W2970608956 @default.
- W4313430026 cites W2972686555 @default.
- W4313430026 cites W2988559779 @default.
- W4313430026 cites W2988640543 @default.
- W4313430026 cites W2990793844 @default.
- W4313430026 cites W2992817139 @default.
- W4313430026 cites W3000505821 @default.
- W4313430026 cites W3003821665 @default.
- W4313430026 cites W3025017204 @default.
- W4313430026 cites W3028754834 @default.
- W4313430026 cites W3102325434 @default.
- W4313430026 cites W3103963684 @default.
- W4313430026 cites W3104804488 @default.
- W4313430026 cites W3180792321 @default.
- W4313430026 cites W3199617720 @default.
- W4313430026 cites W3217269745 @default.
- W4313430026 cites W4200603977 @default.
- W4313430026 cites W4214557309 @default.
- W4313430026 cites W4224244006 @default.
- W4313430026 cites W4243519499 @default.
- W4313430026 doi "https://doi.org/10.1038/s41928-022-00878-9" @default.
- W4313430026 hasPublicationYear "2022" @default.
- W4313430026 type Work @default.
- W4313430026 citedByCount "8" @default.
- W4313430026 countsByYear W43134300262023 @default.
- W4313430026 crossrefType "journal-article" @default.
- W4313430026 hasAuthorship W4313430026A5014138496 @default.
- W4313430026 hasAuthorship W4313430026A5018201019 @default.
- W4313430026 hasAuthorship W4313430026A5027074781 @default.
- W4313430026 hasAuthorship W4313430026A5032249041 @default.
- W4313430026 hasAuthorship W4313430026A5035176203 @default.
- W4313430026 hasAuthorship W4313430026A5055936327 @default.
- W4313430026 hasAuthorship W4313430026A5061181795 @default.
- W4313430026 hasAuthorship W4313430026A5082597513 @default.
- W4313430026 hasAuthorship W4313430026A5090042508 @default.
- W4313430026 hasBestOaLocation W43134300262 @default.
- W4313430026 hasConcept C108583219 @default.
- W4313430026 hasConcept C111919701 @default.
- W4313430026 hasConcept C127413603 @default.
- W4313430026 hasConcept C150072547 @default.
- W4313430026 hasConcept C151927369 @default.
- W4313430026 hasConcept C154945302 @default.
- W4313430026 hasConcept C192562407 @default.
- W4313430026 hasConcept C192576344 @default.
- W4313430026 hasConcept C24326235 @default.
- W4313430026 hasConcept C41008148 @default.
- W4313430026 hasConcept C50644808 @default.