FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4285186484> ?p ?o ?g. }

• W4285186484 endingPage "14" @default.
• W4285186484 startingPage "1" @default.
• W4285186484 abstract "Optical Neural Networks (ONNs) can be promising alternatives for conventional electrical neural networks as they offer ultra-fast data processing with low energy consumption. However, lack of suitable nonlinearity is standing in their way of achieving this goal. While this problem can be circumvented in feed-forward neural networks, the performance of the recurrent neural networks (RNNs) depends heavily on their nonlinearity. In this paper, we first propose and numerically demonstrate a novel reconfigurable optical activation function, named ROA, based on adding or subtracting the outputs of two saturable absorbers (SAs). RAO can provide both bounded and unbounded outputs by facilitating an electrically programmable adder/subtractor design. Second, with the help of RAO, which can be altered to resemble Tanh or Sigmoid activation functions, we take a step further and numerically demonstrate OptoRNN, a new design for an all-optical RNN in free-space optics. Moreover, by benefiting from mathematical modeling of the multiplication noise, as well as an altered loss function, we enable vector-matrix multiplication (VMM) six times more parallel than conventional optical VMM method for the linear part of the OptoRNN. Finally, through comprehensive simulation studies, we demonstrate that utilizing the OptoRNN, we can achieve 96.3% train accuracy for sequential-MNIST dataset." @default.
• W4285186484 created "2022-07-14" @default.
• W4285186484 creator A5051811846 @default.
• W4285186484 creator A5082266911 @default.
• W4285186484 date "2023-03-01" @default.
• W4285186484 modified "2023-10-06" @default.
• W4285186484 title "All-Optical Recurrent Neural Network With Reconfigurable Activation Function" @default.
• W4285186484 cites W1916844592 @default.
• W4285186484 cites W1985530294 @default.
• W4285186484 cites W2054493398 @default.
• W4285186484 cites W2064675550 @default.
• W4285186484 cites W2069854460 @default.
• W4285186484 cites W2081934888 @default.
• W4285186484 cites W2104054098 @default.
• W4285186484 cites W2136016850 @default.
• W4285186484 cites W2150355110 @default.
• W4285186484 cites W2752849906 @default.
• W4285186484 cites W2770947648 @default.
• W4285186484 cites W2783676242 @default.
• W4285186484 cites W2792551587 @default.
• W4285186484 cites W2798701005 @default.
• W4285186484 cites W2887566712 @default.
• W4285186484 cites W2892135951 @default.
• W4285186484 cites W2900709571 @default.
• W4285186484 cites W2901312569 @default.
• W4285186484 cites W2919129235 @default.
• W4285186484 cites W2923894441 @default.
• W4285186484 cites W2955431988 @default.
• W4285186484 cites W2961079966 @default.
• W4285186484 cites W2970080722 @default.
• W4285186484 cites W3010748916 @default.
• W4285186484 cites W3026752472 @default.
• W4285186484 cites W3038988173 @default.
• W4285186484 cites W3096354603 @default.
• W4285186484 cites W3098036526 @default.
• W4285186484 cites W3099341089 @default.
• W4285186484 cites W3105448877 @default.
• W4285186484 cites W3108426037 @default.
• W4285186484 cites W3112468420 @default.
• W4285186484 cites W3121141908 @default.
• W4285186484 cites W3124625166 @default.
• W4285186484 cites W3128062700 @default.
• W4285186484 cites W3128704403 @default.
• W4285186484 cites W3135320274 @default.
• W4285186484 cites W3159854664 @default.
• W4285186484 cites W3165876013 @default.
• W4285186484 cites W74772203 @default.
• W4285186484 doi "https://doi.org/10.1109/jstqe.2022.3173927" @default.
• W4285186484 hasPublicationYear "2023" @default.
• W4285186484 type Work @default.
• W4285186484 citedByCount "3" @default.
• W4285186484 countsByYear W42851864842023 @default.
• W4285186484 crossrefType "journal-article" @default.
• W4285186484 hasAuthorship W4285186484A5051811846 @default.
• W4285186484 hasAuthorship W4285186484A5082266911 @default.
• W4285186484 hasConcept C14036430 @default.
• W4285186484 hasConcept C147168706 @default.
• W4285186484 hasConcept C154945302 @default.
• W4285186484 hasConcept C160724564 @default.
• W4285186484 hasConcept C192562407 @default.
• W4285186484 hasConcept C194232370 @default.
• W4285186484 hasConcept C196129803 @default.
• W4285186484 hasConcept C26840048 @default.
• W4285186484 hasConcept C38365724 @default.
• W4285186484 hasConcept C41008148 @default.
• W4285186484 hasConcept C49040817 @default.
• W4285186484 hasConcept C50644808 @default.
• W4285186484 hasConcept C6260449 @default.
• W4285186484 hasConcept C76155785 @default.
• W4285186484 hasConcept C78458016 @default.
• W4285186484 hasConcept C86803240 @default.
• W4285186484 hasConceptScore W4285186484C14036430 @default.
• W4285186484 hasConceptScore W4285186484C147168706 @default.
• W4285186484 hasConceptScore W4285186484C154945302 @default.
• W4285186484 hasConceptScore W4285186484C160724564 @default.
• W4285186484 hasConceptScore W4285186484C192562407 @default.
• W4285186484 hasConceptScore W4285186484C194232370 @default.
• W4285186484 hasConceptScore W4285186484C196129803 @default.
• W4285186484 hasConceptScore W4285186484C26840048 @default.
• W4285186484 hasConceptScore W4285186484C38365724 @default.
• W4285186484 hasConceptScore W4285186484C41008148 @default.
• W4285186484 hasConceptScore W4285186484C49040817 @default.
• W4285186484 hasConceptScore W4285186484C50644808 @default.
• W4285186484 hasConceptScore W4285186484C6260449 @default.
• W4285186484 hasConceptScore W4285186484C76155785 @default.
• W4285186484 hasConceptScore W4285186484C78458016 @default.
• W4285186484 hasConceptScore W4285186484C86803240 @default.
• W4285186484 hasIssue "2: Optical Computing" @default.
• W4285186484 hasLocation W42851864841 @default.
• W4285186484 hasOpenAccess W4285186484 @default.
• W4285186484 hasPrimaryLocation W42851864841 @default.
• W4285186484 hasRelatedWork W2087204344 @default.
• W4285186484 hasRelatedWork W2137516498 @default.
• W4285186484 hasRelatedWork W2147776231 @default.
• W4285186484 hasRelatedWork W2792268997 @default.
• W4285186484 hasRelatedWork W2902723393 @default.
• W4285186484 hasRelatedWork W2998088892 @default.
• W4285186484 hasRelatedWork W3012292080 @default.

• next