Matches in SemOpenAlex for { <https://semopenalex.org/work/W2916236435> ?p ?o ?g. }
Showing items 1 to 99 of
99
with 100 items per page.
- W2916236435 endingPage "126" @default.
- W2916236435 startingPage "121" @default.
- W2916236435 abstract "The demand for high speed data transmission has increased rapidly over the past few years, leading to the development of the data center concept. Considering that vertical cavity surface emitting lasers (VCSELs) based optical interconnect is evolving to 100 Gb/s, relative intensity noise and mode partition noise are becoming significant, which cannot be equalized by conventional equalizers efficiently. On the other hand, optical fiber suffers from inter-symbol interference (ISI) and nonlinear channel response, making the equalization process even more challenging. Recently, several machine learning techniques have already been applied to recover signal from nonlinear distortions. However, previous experiments mainly focused on achieving low BER and have neglected the computational complexity. In this paper, we have designed a recurrent neural network (RNN) based equalizer. The equalizer is tested over a PAM-4 modulated VCSEL-MMF optical interconnect link, and shows BER performance improvement over equalizers based on ANN. A variant, Half-RNN, is also proposed and tested, whose computational complexity is 70% lower than ANN with similar BER performance. Our experiments provide guidance for designing neural network structure when using deep learning for equalization, justifying the significance of our work." @default.
- W2916236435 created "2019-03-02" @default.
- W2916236435 creator A5030048520 @default.
- W2916236435 creator A5055311268 @default.
- W2916236435 creator A5060249411 @default.
- W2916236435 creator A5060991331 @default.
- W2916236435 creator A5086363082 @default.
- W2916236435 date "2019-06-01" @default.
- W2916236435 modified "2023-10-14" @default.
- W2916236435 title "Low computationally complex recurrent neural network for high speed optical fiber transmission" @default.
- W2916236435 cites W1995082601 @default.
- W2916236435 cites W2030249347 @default.
- W2916236435 cites W2518340429 @default.
- W2916236435 cites W2527155311 @default.
- W2916236435 cites W2552275234 @default.
- W2916236435 cites W2564784366 @default.
- W2916236435 cites W2595339838 @default.
- W2916236435 cites W2597326733 @default.
- W2916236435 cites W2734408173 @default.
- W2916236435 cites W2811293019 @default.
- W2916236435 doi "https://doi.org/10.1016/j.optcom.2019.02.037" @default.
- W2916236435 hasPublicationYear "2019" @default.
- W2916236435 type Work @default.
- W2916236435 sameAs 2916236435 @default.
- W2916236435 citedByCount "28" @default.
- W2916236435 countsByYear W29162364352019 @default.
- W2916236435 countsByYear W29162364352020 @default.
- W2916236435 countsByYear W29162364352021 @default.
- W2916236435 countsByYear W29162364352022 @default.
- W2916236435 countsByYear W29162364352023 @default.
- W2916236435 crossrefType "journal-article" @default.
- W2916236435 hasAuthorship W2916236435A5030048520 @default.
- W2916236435 hasAuthorship W2916236435A5055311268 @default.
- W2916236435 hasAuthorship W2916236435A5060249411 @default.
- W2916236435 hasAuthorship W2916236435A5060991331 @default.
- W2916236435 hasAuthorship W2916236435A5086363082 @default.
- W2916236435 hasConcept C115961682 @default.
- W2916236435 hasConcept C120665830 @default.
- W2916236435 hasConcept C121332964 @default.
- W2916236435 hasConcept C123745756 @default.
- W2916236435 hasConcept C127162648 @default.
- W2916236435 hasConcept C127413603 @default.
- W2916236435 hasConcept C147168706 @default.
- W2916236435 hasConcept C154945302 @default.
- W2916236435 hasConcept C158622935 @default.
- W2916236435 hasConcept C24326235 @default.
- W2916236435 hasConcept C2777759342 @default.
- W2916236435 hasConcept C31258907 @default.
- W2916236435 hasConcept C41008148 @default.
- W2916236435 hasConcept C50644808 @default.
- W2916236435 hasConcept C557945733 @default.
- W2916236435 hasConcept C62520636 @default.
- W2916236435 hasConcept C75755367 @default.
- W2916236435 hasConcept C761482 @default.
- W2916236435 hasConcept C76155785 @default.
- W2916236435 hasConcept C97812054 @default.
- W2916236435 hasConcept C99498987 @default.
- W2916236435 hasConceptScore W2916236435C115961682 @default.
- W2916236435 hasConceptScore W2916236435C120665830 @default.
- W2916236435 hasConceptScore W2916236435C121332964 @default.
- W2916236435 hasConceptScore W2916236435C123745756 @default.
- W2916236435 hasConceptScore W2916236435C127162648 @default.
- W2916236435 hasConceptScore W2916236435C127413603 @default.
- W2916236435 hasConceptScore W2916236435C147168706 @default.
- W2916236435 hasConceptScore W2916236435C154945302 @default.
- W2916236435 hasConceptScore W2916236435C158622935 @default.
- W2916236435 hasConceptScore W2916236435C24326235 @default.
- W2916236435 hasConceptScore W2916236435C2777759342 @default.
- W2916236435 hasConceptScore W2916236435C31258907 @default.
- W2916236435 hasConceptScore W2916236435C41008148 @default.
- W2916236435 hasConceptScore W2916236435C50644808 @default.
- W2916236435 hasConceptScore W2916236435C557945733 @default.
- W2916236435 hasConceptScore W2916236435C62520636 @default.
- W2916236435 hasConceptScore W2916236435C75755367 @default.
- W2916236435 hasConceptScore W2916236435C761482 @default.
- W2916236435 hasConceptScore W2916236435C76155785 @default.
- W2916236435 hasConceptScore W2916236435C97812054 @default.
- W2916236435 hasConceptScore W2916236435C99498987 @default.
- W2916236435 hasFunder F4320326705 @default.
- W2916236435 hasLocation W29162364351 @default.
- W2916236435 hasOpenAccess W2916236435 @default.
- W2916236435 hasPrimaryLocation W29162364351 @default.
- W2916236435 hasRelatedWork W1487325857 @default.
- W2916236435 hasRelatedWork W1954193021 @default.
- W2916236435 hasRelatedWork W2027536103 @default.
- W2916236435 hasRelatedWork W2103401693 @default.
- W2916236435 hasRelatedWork W2170787009 @default.
- W2916236435 hasRelatedWork W2512076603 @default.
- W2916236435 hasRelatedWork W2535561909 @default.
- W2916236435 hasRelatedWork W2545738516 @default.
- W2916236435 hasRelatedWork W3112720982 @default.
- W2916236435 hasRelatedWork W2982846611 @default.
- W2916236435 hasVolume "441" @default.
- W2916236435 isParatext "false" @default.
- W2916236435 isRetracted "false" @default.
- W2916236435 magId "2916236435" @default.
- W2916236435 workType "article" @default.