Matches in SemOpenAlex for { <https://semopenalex.org/work/W4287760650> ?p ?o ?g. }
Showing items 1 to 58 of
58
with 100 items per page.
- W4287760650 abstract "We propose a diffractive neural network with strong robustness based on Weight Noise Injection training, which achieves accurate and fast optical-based classification while diffraction layers have a certain amount of surface shape error. To the best of our knowledge, it is the first time that using injection weight noise during training to reduce the impact of external interference on deep learning inference results. In the proposed method, the diffractive neural network learns the mapping between the input image and the label in Weight Noise Injection mode, making the network's weight insensitive to modest changes, which improve the network's noise resistance at a lower cost. By comparing the accuracy of the network under different noise, it is verified that the proposed network (SRNN) still maintains a higher accuracy under serious noise." @default.
- W4287760650 created "2022-07-26" @default.
- W4287760650 creator A5038318417 @default.
- W4287760650 date "2020-06-08" @default.
- W4287760650 modified "2023-09-26" @default.
- W4287760650 title "A Diffractive Neural Network with Weight-Noise-Injection Training" @default.
- W4287760650 hasPublicationYear "2020" @default.
- W4287760650 type Work @default.
- W4287760650 citedByCount "0" @default.
- W4287760650 crossrefType "posted-content" @default.
- W4287760650 hasAuthorship W4287760650A5038318417 @default.
- W4287760650 hasBestOaLocation W42877606501 @default.
- W4287760650 hasConcept C104317684 @default.
- W4287760650 hasConcept C115961682 @default.
- W4287760650 hasConcept C119857082 @default.
- W4287760650 hasConcept C127162648 @default.
- W4287760650 hasConcept C153180895 @default.
- W4287760650 hasConcept C154945302 @default.
- W4287760650 hasConcept C185592680 @default.
- W4287760650 hasConcept C2776214188 @default.
- W4287760650 hasConcept C32022120 @default.
- W4287760650 hasConcept C41008148 @default.
- W4287760650 hasConcept C50644808 @default.
- W4287760650 hasConcept C55493867 @default.
- W4287760650 hasConcept C63479239 @default.
- W4287760650 hasConcept C76155785 @default.
- W4287760650 hasConcept C99498987 @default.
- W4287760650 hasConceptScore W4287760650C104317684 @default.
- W4287760650 hasConceptScore W4287760650C115961682 @default.
- W4287760650 hasConceptScore W4287760650C119857082 @default.
- W4287760650 hasConceptScore W4287760650C127162648 @default.
- W4287760650 hasConceptScore W4287760650C153180895 @default.
- W4287760650 hasConceptScore W4287760650C154945302 @default.
- W4287760650 hasConceptScore W4287760650C185592680 @default.
- W4287760650 hasConceptScore W4287760650C2776214188 @default.
- W4287760650 hasConceptScore W4287760650C32022120 @default.
- W4287760650 hasConceptScore W4287760650C41008148 @default.
- W4287760650 hasConceptScore W4287760650C50644808 @default.
- W4287760650 hasConceptScore W4287760650C55493867 @default.
- W4287760650 hasConceptScore W4287760650C63479239 @default.
- W4287760650 hasConceptScore W4287760650C76155785 @default.
- W4287760650 hasConceptScore W4287760650C99498987 @default.
- W4287760650 hasLocation W42877606501 @default.
- W4287760650 hasOpenAccess W4287760650 @default.
- W4287760650 hasPrimaryLocation W42877606501 @default.
- W4287760650 hasRelatedWork W11300528 @default.
- W4287760650 hasRelatedWork W13920906 @default.
- W4287760650 hasRelatedWork W2305996 @default.
- W4287760650 hasRelatedWork W3092890 @default.
- W4287760650 hasRelatedWork W5477720 @default.
- W4287760650 hasRelatedWork W6770330 @default.
- W4287760650 hasRelatedWork W6882942 @default.
- W4287760650 hasRelatedWork W8235949 @default.
- W4287760650 hasRelatedWork W8315361 @default.
- W4287760650 hasRelatedWork W9463276 @default.
- W4287760650 isParatext "false" @default.
- W4287760650 isRetracted "false" @default.
- W4287760650 workType "article" @default.