Matches in SemOpenAlex for { <https://semopenalex.org/work/W4380355087> ?p ?o ?g. }
- W4380355087 endingPage "22127" @default.
- W4380355087 startingPage "22127" @default.
- W4380355087 abstract "A new method to improve the integration level of an on-chip diffractive optical neural network (DONN) is proposed based on a standard silicon-on-insulator (SOI) platform. The metaline, which represents a hidden layer in the integrated on-chip DONN, is composed of subwavelength silica slots, providing a large computation capacity. However, the physical propagation process of light in the subwavelength metalinses generally requires an approximate characterization using slot groups and extra length between adjacent layers, which limits further improvements of the integration of on-chip DONN. In this work, a deep mapping regression model (DMRM) is proposed to characterize the process of light propagation in the metalines. This method improves the integration level of on-chip DONN to over 60,000 and elimnates the need for approximate conditions. Based on this theory, a compact-DONN (C-DONN) is exploited and benchmarked on the Iris plants dataset to verify the performance, yielding a testing accuracy of 93.3%. This method provides a potential solution for future large-scale on-chip integration." @default.
- W4380355087 created "2023-06-13" @default.
- W4380355087 creator A5004467877 @default.
- W4380355087 creator A5006519315 @default.
- W4380355087 creator A5020540940 @default.
- W4380355087 creator A5031385658 @default.
- W4380355087 creator A5060183562 @default.
- W4380355087 creator A5086225982 @default.
- W4380355087 date "2023-06-15" @default.
- W4380355087 modified "2023-09-27" @default.
- W4380355087 title "C-DONN: compact diffractive optical neural network with deep learning regression" @default.
- W4380355087 cites W2164727176 @default.
- W4380355087 cites W2502949459 @default.
- W4380355087 cites W2592929672 @default.
- W4380355087 cites W2618530766 @default.
- W4380355087 cites W2752849906 @default.
- W4380355087 cites W2770947648 @default.
- W4380355087 cites W2775280502 @default.
- W4380355087 cites W2798701005 @default.
- W4380355087 cites W2895491352 @default.
- W4380355087 cites W2919115771 @default.
- W4380355087 cites W2944119451 @default.
- W4380355087 cites W2956121443 @default.
- W4380355087 cites W2961079966 @default.
- W4380355087 cites W2964082513 @default.
- W4380355087 cites W2966722031 @default.
- W4380355087 cites W2975079120 @default.
- W4380355087 cites W3098290163 @default.
- W4380355087 cites W3098457739 @default.
- W4380355087 cites W3103046660 @default.
- W4380355087 cites W3120165331 @default.
- W4380355087 cites W3121141908 @default.
- W4380355087 cites W3156357868 @default.
- W4380355087 cites W3200289607 @default.
- W4380355087 cites W3210322523 @default.
- W4380355087 cites W3216922697 @default.
- W4380355087 cites W4213428796 @default.
- W4380355087 cites W4224942320 @default.
- W4380355087 cites W4226191790 @default.
- W4380355087 cites W4281845262 @default.
- W4380355087 cites W4292230258 @default.
- W4380355087 cites W4296701503 @default.
- W4380355087 cites W4313576662 @default.
- W4380355087 cites W4366140936 @default.
- W4380355087 doi "https://doi.org/10.1364/oe.490072" @default.
- W4380355087 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/37381294" @default.
- W4380355087 hasPublicationYear "2023" @default.
- W4380355087 type Work @default.
- W4380355087 citedByCount "0" @default.
- W4380355087 crossrefType "journal-article" @default.
- W4380355087 hasAuthorship W4380355087A5004467877 @default.
- W4380355087 hasAuthorship W4380355087A5006519315 @default.
- W4380355087 hasAuthorship W4380355087A5020540940 @default.
- W4380355087 hasAuthorship W4380355087A5031385658 @default.
- W4380355087 hasAuthorship W4380355087A5060183562 @default.
- W4380355087 hasAuthorship W4380355087A5086225982 @default.
- W4380355087 hasBestOaLocation W43803550871 @default.
- W4380355087 hasConcept C111919701 @default.
- W4380355087 hasConcept C11413529 @default.
- W4380355087 hasConcept C120665830 @default.
- W4380355087 hasConcept C121332964 @default.
- W4380355087 hasConcept C127413603 @default.
- W4380355087 hasConcept C154945302 @default.
- W4380355087 hasConcept C165005293 @default.
- W4380355087 hasConcept C192562407 @default.
- W4380355087 hasConcept C24326235 @default.
- W4380355087 hasConcept C41008148 @default.
- W4380355087 hasConcept C45374587 @default.
- W4380355087 hasConcept C459310 @default.
- W4380355087 hasConcept C49040817 @default.
- W4380355087 hasConcept C50644808 @default.
- W4380355087 hasConcept C53143962 @default.
- W4380355087 hasConcept C544956773 @default.
- W4380355087 hasConcept C76155785 @default.
- W4380355087 hasConcept C98045186 @default.
- W4380355087 hasConceptScore W4380355087C111919701 @default.
- W4380355087 hasConceptScore W4380355087C11413529 @default.
- W4380355087 hasConceptScore W4380355087C120665830 @default.
- W4380355087 hasConceptScore W4380355087C121332964 @default.
- W4380355087 hasConceptScore W4380355087C127413603 @default.
- W4380355087 hasConceptScore W4380355087C154945302 @default.
- W4380355087 hasConceptScore W4380355087C165005293 @default.
- W4380355087 hasConceptScore W4380355087C192562407 @default.
- W4380355087 hasConceptScore W4380355087C24326235 @default.
- W4380355087 hasConceptScore W4380355087C41008148 @default.
- W4380355087 hasConceptScore W4380355087C45374587 @default.
- W4380355087 hasConceptScore W4380355087C459310 @default.
- W4380355087 hasConceptScore W4380355087C49040817 @default.
- W4380355087 hasConceptScore W4380355087C50644808 @default.
- W4380355087 hasConceptScore W4380355087C53143962 @default.
- W4380355087 hasConceptScore W4380355087C544956773 @default.
- W4380355087 hasConceptScore W4380355087C76155785 @default.
- W4380355087 hasConceptScore W4380355087C98045186 @default.
- W4380355087 hasFunder F4320321001 @default.
- W4380355087 hasFunder F4320325902 @default.
- W4380355087 hasIssue "13" @default.
- W4380355087 hasLocation W43803550871 @default.
- W4380355087 hasLocation W43803550872 @default.