FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4315926504> ?p ?o ?g. }

• W4315926504 endingPage "014003" @default.
• W4315926504 startingPage "014003" @default.
• W4315926504 abstract "Abstract Memristors, emerging non-volatile memory devices, have shown promising potential in neuromorphic hardware designs, especially in spiking neural network (SNN) hardware implementation. Memristor-based SNNs have been successfully applied in a wide range of applications, including image classification and pattern recognition. However, implementing memristor-based SNNs in text classification is still under exploration. One of the main reasons is that training memristor-based SNNs for text classification is costly due to the lack of efficient learning rules and memristor non-idealities. To address these issues and accelerate the research of exploring memristor-based SNNs in text classification applications, we develop a simulation framework with a virtual memristor array using an empirical memristor model. We use this framework to demonstrate a sentiment analysis task in the IMDB movie reviews dataset. We take two approaches to obtain trained SNNs with memristor models: (1) by converting a pre-trained artificial neural network (ANN) to a memristor-based SNN, or (2) by training a memristor-based SNN directly. These two approaches can be applied in two scenarios: offline classification and online training. We achieve the classification accuracy of 85.88% by converting a pre-trained ANN to a memristor-based SNN and 84.86% by training the memristor-based SNN directly, given that the baseline training accuracy of the equivalent ANN is 86.02%. We conclude that it is possible to achieve similar classification accuracy in simulation from ANNs to SNNs and from non-memristive synapses to data-driven memristive synapses. We also investigate how global parameters such as spike train length, the read noise, and the weight updating stop conditions affect the neural networks in both approaches. This investigation further indicates that the simulation using statistic memristor models in the two approaches presented by this paper can assist the exploration of memristor-based SNNs in natural language processing tasks." @default.
• W4315926504 created "2023-01-14" @default.
• W4315926504 creator A5017301291 @default.
• W4315926504 creator A5051954648 @default.
• W4315926504 creator A5056739019 @default.
• W4315926504 creator A5088089733 @default.
• W4315926504 date "2023-01-31" @default.
• W4315926504 modified "2023-09-30" @default.
• W4315926504 title "Text classification in memristor-based spiking neural networks" @default.
• W4315926504 cites W101771737 @default.
• W4315926504 cites W1498436455 @default.
• W4315926504 cites W1580086694 @default.
• W4315926504 cites W1604973310 @default.
• W4315926504 cites W1606057915 @default.
• W4315926504 cites W1645800954 @default.
• W4315926504 cites W1658307413 @default.
• W4315926504 cites W186834029 @default.
• W4315926504 cites W1974027339 @default.
• W4315926504 cites W2008008156 @default.
• W4315926504 cites W2020676607 @default.
• W4315926504 cites W2033365336 @default.
• W4315926504 cites W2042013578 @default.
• W4315926504 cites W2076646500 @default.
• W4315926504 cites W2076964542 @default.
• W4315926504 cites W2082690044 @default.
• W4315926504 cites W2088192327 @default.
• W4315926504 cites W2097446068 @default.
• W4315926504 cites W2102397476 @default.
• W4315926504 cites W2120615054 @default.
• W4315926504 cites W2127313932 @default.
• W4315926504 cites W2127712540 @default.
• W4315926504 cites W2129788035 @default.
• W4315926504 cites W2130360162 @default.
• W4315926504 cites W2130388397 @default.
• W4315926504 cites W2136251560 @default.
• W4315926504 cites W2170942403 @default.
• W4315926504 cites W2172307690 @default.
• W4315926504 cites W2250539671 @default.
• W4315926504 cites W2283674326 @default.
• W4315926504 cites W2321026975 @default.
• W4315926504 cites W2397312330 @default.
• W4315926504 cites W2470673105 @default.
• W4315926504 cites W2512574110 @default.
• W4315926504 cites W2525649597 @default.
• W4315926504 cites W2532666972 @default.
• W4315926504 cites W2550740543 @default.
• W4315926504 cites W2605663629 @default.
• W4315926504 cites W2606722458 @default.
• W4315926504 cites W2736591611 @default.
• W4315926504 cites W2760607949 @default.
• W4315926504 cites W2769049661 @default.
• W4315926504 cites W2775079417 @default.
• W4315926504 cites W2782046614 @default.
• W4315926504 cites W2783525259 @default.
• W4315926504 cites W2790556218 @default.
• W4315926504 cites W2792773193 @default.
• W4315926504 cites W2800881502 @default.
• W4315926504 cites W2803163155 @default.
• W4315926504 cites W2807894615 @default.
• W4315926504 cites W2883283267 @default.
• W4315926504 cites W2909800597 @default.
• W4315926504 cites W2962953132 @default.
• W4315926504 cites W2963341956 @default.
• W4315926504 cites W2963355447 @default.
• W4315926504 cites W2963817554 @default.
• W4315926504 cites W2963887423 @default.
• W4315926504 cites W2964338223 @default.
• W4315926504 cites W2976523354 @default.
• W4315926504 cites W2984707426 @default.
• W4315926504 cites W2998119008 @default.
• W4315926504 cites W3003821665 @default.
• W4315926504 cites W3035400263 @default.
• W4315926504 cites W3043133474 @default.
• W4315926504 cites W3107362149 @default.
• W4315926504 cites W3129643976 @default.
• W4315926504 cites W4213419759 @default.
• W4315926504 cites W4224223814 @default.
• W4315926504 cites W4238614602 @default.
• W4315926504 cites W4292266506 @default.
• W4315926504 cites W2185212694 @default.
• W4315926504 doi "https://doi.org/10.1088/2634-4386/acb2f0" @default.
• W4315926504 hasPublicationYear "2023" @default.
• W4315926504 type Work @default.
• W4315926504 citedByCount "2" @default.
• W4315926504 countsByYear W43159265042023 @default.
• W4315926504 crossrefType "journal-article" @default.
• W4315926504 hasAuthorship W4315926504A5017301291 @default.
• W4315926504 hasAuthorship W4315926504A5051954648 @default.
• W4315926504 hasAuthorship W4315926504A5056739019 @default.
• W4315926504 hasAuthorship W4315926504A5088089733 @default.
• W4315926504 hasBestOaLocation W43159265041 @default.
• W4315926504 hasConcept C11731999 @default.
• W4315926504 hasConcept C119599485 @default.
• W4315926504 hasConcept C119857082 @default.
• W4315926504 hasConcept C127413603 @default.
• W4315926504 hasConcept C150072547 @default.
• W4315926504 hasConcept C151927369 @default.
• W4315926504 hasConcept C153180895 @default.

• next