FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4385497312> ?p ?o ?g. }

• W4385497312 endingPage "28489" @default.
• W4385497312 startingPage "28489" @default.
• W4385497312 abstract "Spiking neural networks (SNNs) offer powerful computation capability due to its event-driven nature and temporal processing. However, it is still limited to shallow structure and simple tasks due to the training difficulty. In this work, we propose a deep convolutional residual spiking neural network (DCRSNN) for text classification tasks. In the DCRSNN, the feature extraction is achieved via a convolution SNN with residual connection, using the surrogate gradient direct training technique. Classification is performed by a fully-connected network. We also suggest a hybrid photonic DCRSNN, in which photonic SNNs are used for classification with a converted training method. The accuracy of hard and soft reset methods, as well as three different surrogate functions, were evaluated and compared across four different datasets. Results indicated a maximum accuracy of 76.36% for MR, 91.03% for AG News, 88.06% for IMDB and 93.99% for Yelp review polarity. Soft reset methods used in the deep convolutional SNN yielded slightly better accuracy than their hard reset counterparts. We also considered the effects of different pooling methods and observation time windows and found that the convergence accuracy achieved by convolutional SNNs was comparable to that of convolutional neural networks under the same conditions. Moreover, the hybrid photonic DCRSNN also shows comparable testing accuracy. This work provides new insights into extending the SNN applications in the field of text classification and natural language processing, which is interesting for the resources-restrained scenarios." @default.
• W4385497312 created "2023-08-03" @default.
• W4385497312 creator A5034972378 @default.
• W4385497312 creator A5038033297 @default.
• W4385497312 creator A5045398469 @default.
• W4385497312 creator A5052796126 @default.
• W4385497312 creator A5053337495 @default.
• W4385497312 creator A5067368540 @default.
• W4385497312 creator A5069555022 @default.
• W4385497312 creator A5070942254 @default.
• W4385497312 date "2023-08-10" @default.
• W4385497312 modified "2023-10-14" @default.
• W4385497312 title "Hybrid photonic deep convolutional residual spiking neural networks for text classification" @default.
• W4385497312 cites W101771737 @default.
• W4385497312 cites W1570411240 @default.
• W4385497312 cites W1663984431 @default.
• W4385497312 cites W2007815184 @default.
• W4385497312 cites W2020676607 @default.
• W4385497312 cites W2115831804 @default.
• W4385497312 cites W2157239334 @default.
• W4385497312 cites W2165639766 @default.
• W4385497312 cites W2401577158 @default.
• W4385497312 cites W2569813014 @default.
• W4385497312 cites W2621826044 @default.
• W4385497312 cites W2739588406 @default.
• W4385497312 cites W2752849906 @default.
• W4385497312 cites W2775079417 @default.
• W4385497312 cites W2939710518 @default.
• W4385497312 cites W2944119451 @default.
• W4385497312 cites W2964121744 @default.
• W4385497312 cites W2964338223 @default.
• W4385497312 cites W2976834111 @default.
• W4385497312 cites W2979879900 @default.
• W4385497312 cites W2984844508 @default.
• W4385497312 cites W2990793844 @default.
• W4385497312 cites W3014583102 @default.
• W4385497312 cites W3041827902 @default.
• W4385497312 cites W3043463905 @default.
• W4385497312 cites W3128451613 @default.
• W4385497312 cites W3128915407 @default.
• W4385497312 cites W3164933491 @default.
• W4385497312 cites W4205804651 @default.
• W4385497312 cites W4210357113 @default.
• W4385497312 cites W4233876794 @default.
• W4385497312 cites W4283801924 @default.
• W4385497312 cites W4292826019 @default.
• W4385497312 cites W4309944398 @default.
• W4385497312 cites W4312134097 @default.
• W4385497312 cites W4315926504 @default.
• W4385497312 cites W4376878196 @default.
• W4385497312 doi "https://doi.org/10.1364/oe.497218" @default.
• W4385497312 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/37710902" @default.
• W4385497312 hasPublicationYear "2023" @default.
• W4385497312 type Work @default.
• W4385497312 citedByCount "0" @default.
• W4385497312 crossrefType "journal-article" @default.
• W4385497312 hasAuthorship W4385497312A5034972378 @default.
• W4385497312 hasAuthorship W4385497312A5038033297 @default.
• W4385497312 hasAuthorship W4385497312A5045398469 @default.
• W4385497312 hasAuthorship W4385497312A5052796126 @default.
• W4385497312 hasAuthorship W4385497312A5053337495 @default.
• W4385497312 hasAuthorship W4385497312A5067368540 @default.
• W4385497312 hasAuthorship W4385497312A5069555022 @default.
• W4385497312 hasAuthorship W4385497312A5070942254 @default.
• W4385497312 hasBestOaLocation W43854973121 @default.
• W4385497312 hasConcept C108583219 @default.
• W4385497312 hasConcept C11413529 @default.
• W4385497312 hasConcept C153180895 @default.
• W4385497312 hasConcept C154945302 @default.
• W4385497312 hasConcept C155512373 @default.
• W4385497312 hasConcept C41008148 @default.
• W4385497312 hasConcept C45347329 @default.
• W4385497312 hasConcept C50644808 @default.
• W4385497312 hasConcept C52622490 @default.
• W4385497312 hasConcept C70437156 @default.
• W4385497312 hasConcept C81363708 @default.
• W4385497312 hasConceptScore W4385497312C108583219 @default.
• W4385497312 hasConceptScore W4385497312C11413529 @default.
• W4385497312 hasConceptScore W4385497312C153180895 @default.
• W4385497312 hasConceptScore W4385497312C154945302 @default.
• W4385497312 hasConceptScore W4385497312C155512373 @default.
• W4385497312 hasConceptScore W4385497312C41008148 @default.
• W4385497312 hasConceptScore W4385497312C45347329 @default.
• W4385497312 hasConceptScore W4385497312C50644808 @default.
• W4385497312 hasConceptScore W4385497312C52622490 @default.
• W4385497312 hasConceptScore W4385497312C70437156 @default.
• W4385497312 hasConceptScore W4385497312C81363708 @default.
• W4385497312 hasFunder F4320321001 @default.
• W4385497312 hasFunder F4320333688 @default.
• W4385497312 hasFunder F4320335777 @default.
• W4385497312 hasFunder F4320335787 @default.
• W4385497312 hasIssue "17" @default.
• W4385497312 hasLocation W43854973121 @default.
• W4385497312 hasLocation W43854973122 @default.
• W4385497312 hasOpenAccess W4385497312 @default.
• W4385497312 hasPrimaryLocation W43854973121 @default.
• W4385497312 hasRelatedWork W2279398222 @default.
• W4385497312 hasRelatedWork W2517027266 @default.

• next