FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4382371099> ?p ?o ?g. }

• W4382371099 endingPage "887" @default.
• W4382371099 startingPage "878" @default.
• W4382371099 abstract "On-chip interconnects are very important in both integrated circuits and systems, affecting the signal transmission directly. To design the interconnects with better performance, designers usually rely on the heuristic methods and even rules of thumb with high labor resources. To alleviate this issue, the transfer learning-based deep neural networks (TL-DNN) are proposed to realize inverse and fully-automatic design of the on-chip interconnects. Such TL-DNN-based surrogate model consists of two DNNs. The first DNN is employed to map the performance parameters to the geometric parameters in the equivalent circuit space, where the trained hyper-parameters of the first DNN are transferred to the second DNN model. Further, 300 data sets from the in-house electromagnetic (EM) parallel solver space are generated and used to train the second DNN, with 3000 data sets used for testing. Compared with the DNN-based and deep hybrid neural network (HDNN)-based inverse design methods, the proposed method not only achieves a high testing accuracy (93.67%), but requires only 6.15 hours of modelling time. In addition, the well-trained model has the ability to achieve the desired design specification within a fraction of seconds, compared to the hours-days-weeks of the forward design approach. An elaborate interconnect prototype is fabricated, and its measured results fully satisfy the performance demands. It is expected that the proposed modelling scheme can be used for the design of many interconnects." @default.
• W4382371099 created "2023-06-29" @default.
• W4382371099 creator A5006466366 @default.
• W4382371099 creator A5029718819 @default.
• W4382371099 creator A5034083498 @default.
• W4382371099 creator A5041364072 @default.
• W4382371099 creator A5055034461 @default.
• W4382371099 date "2023-06-01" @default.
• W4382371099 modified "2023-09-25" @default.
• W4382371099 title "Inverse Design of On-Chip Interconnect via Transfer Learning-Based Deep Neural Networks" @default.
• W4382371099 cites W1926811926 @default.
• W4382371099 cites W2005346062 @default.
• W4382371099 cites W2072302933 @default.
• W4382371099 cites W2103529678 @default.
• W4382371099 cites W2103656882 @default.
• W4382371099 cites W2104240799 @default.
• W4382371099 cites W2106503622 @default.
• W4382371099 cites W2137893918 @default.
• W4382371099 cites W2139216877 @default.
• W4382371099 cites W2317953216 @default.
• W4382371099 cites W2346062042 @default.
• W4382371099 cites W2522653451 @default.
• W4382371099 cites W2790997597 @default.
• W4382371099 cites W2808610260 @default.
• W4382371099 cites W2966623823 @default.
• W4382371099 cites W2972911849 @default.
• W4382371099 cites W2975830944 @default.
• W4382371099 cites W2982632291 @default.
• W4382371099 cites W3081131991 @default.
• W4382371099 cites W3097413296 @default.
• W4382371099 cites W3141617231 @default.
• W4382371099 cites W3166117426 @default.
• W4382371099 cites W3185928300 @default.
• W4382371099 cites W3207655436 @default.
• W4382371099 cites W4205774390 @default.
• W4382371099 cites W4225725044 @default.
• W4382371099 cites W4226048752 @default.
• W4382371099 cites W4284892856 @default.
• W4382371099 cites W4285251510 @default.
• W4382371099 cites W4292348086 @default.
• W4382371099 cites W4296915750 @default.
• W4382371099 cites W4313590988 @default.
• W4382371099 cites W44815768 @default.
• W4382371099 doi "https://doi.org/10.1109/tcpmt.2023.3290413" @default.
• W4382371099 hasPublicationYear "2023" @default.
• W4382371099 type Work @default.
• W4382371099 citedByCount "0" @default.
• W4382371099 crossrefType "journal-article" @default.
• W4382371099 hasAuthorship W4382371099A5006466366 @default.
• W4382371099 hasAuthorship W4382371099A5029718819 @default.
• W4382371099 hasAuthorship W4382371099A5034083498 @default.
• W4382371099 hasAuthorship W4382371099A5041364072 @default.
• W4382371099 hasAuthorship W4382371099A5055034461 @default.
• W4382371099 hasConcept C108583219 @default.
• W4382371099 hasConcept C113775141 @default.
• W4382371099 hasConcept C123745756 @default.
• W4382371099 hasConcept C127413603 @default.
• W4382371099 hasConcept C154945302 @default.
• W4382371099 hasConcept C165005293 @default.
• W4382371099 hasConcept C173801870 @default.
• W4382371099 hasConcept C199360897 @default.
• W4382371099 hasConcept C207467116 @default.
• W4382371099 hasConcept C24326235 @default.
• W4382371099 hasConcept C2524010 @default.
• W4382371099 hasConcept C2778770139 @default.
• W4382371099 hasConcept C31258907 @default.
• W4382371099 hasConcept C33923547 @default.
• W4382371099 hasConcept C41008148 @default.
• W4382371099 hasConcept C50644808 @default.
• W4382371099 hasConcept C76155785 @default.
• W4382371099 hasConceptScore W4382371099C108583219 @default.
• W4382371099 hasConceptScore W4382371099C113775141 @default.
• W4382371099 hasConceptScore W4382371099C123745756 @default.
• W4382371099 hasConceptScore W4382371099C127413603 @default.
• W4382371099 hasConceptScore W4382371099C154945302 @default.
• W4382371099 hasConceptScore W4382371099C165005293 @default.
• W4382371099 hasConceptScore W4382371099C173801870 @default.
• W4382371099 hasConceptScore W4382371099C199360897 @default.
• W4382371099 hasConceptScore W4382371099C207467116 @default.
• W4382371099 hasConceptScore W4382371099C24326235 @default.
• W4382371099 hasConceptScore W4382371099C2524010 @default.
• W4382371099 hasConceptScore W4382371099C2778770139 @default.
• W4382371099 hasConceptScore W4382371099C31258907 @default.
• W4382371099 hasConceptScore W4382371099C33923547 @default.
• W4382371099 hasConceptScore W4382371099C41008148 @default.
• W4382371099 hasConceptScore W4382371099C50644808 @default.
• W4382371099 hasConceptScore W4382371099C76155785 @default.
• W4382371099 hasFunder F4320321001 @default.
• W4382371099 hasIssue "6" @default.
• W4382371099 hasLocation W43823710991 @default.
• W4382371099 hasOpenAccess W4382371099 @default.
• W4382371099 hasPrimaryLocation W43823710991 @default.
• W4382371099 hasRelatedWork W1511998565 @default.
• W4382371099 hasRelatedWork W2126887587 @default.
• W4382371099 hasRelatedWork W2731899572 @default.
• W4382371099 hasRelatedWork W2939353110 @default.
• W4382371099 hasRelatedWork W3009238340 @default.
• W4382371099 hasRelatedWork W3215138031 @default.

• next