Matches in SemOpenAlex for { <https://semopenalex.org/work/W4307366305> ?p ?o ?g. }
- W4307366305 endingPage "18" @default.
- W4307366305 startingPage "1" @default.
- W4307366305 abstract "Performing chemical mechanical polishing (CMP) modeling for physical verification on an integrated circuit (IC) chip is vital to minimize its manufacturing yield loss. Traditional CMP models calculate post-CMP topography height of the IC’s layout based on physical principles and empirical experiments, which is computationally costly and time-consuming. In this work, we propose a CmpCNN framework based on convolutional neural networks (CNNs) with a transfer learning method to accelerate the CMP modeling process. It utilizes a multi-input strategy by feeding the binary image of layout and its density into our CNN-based model to extract features more efficiently. The transfer learning method is adopted to different CMP process parameters and different categories of circuits to further improve its prediction accuracy and convergence speed. Experimental results show that our CmpCNN framework achieves a competitive root mean square error ( RMSE ) of 2.7733Å with 1.89× reduction compared to the prior work, and a 57× speedup compared to the commercial CMP simulation tool." @default.
- W4307366305 created "2022-10-31" @default.
- W4307366305 creator A5002688054 @default.
- W4307366305 creator A5009236768 @default.
- W4307366305 creator A5025851882 @default.
- W4307366305 creator A5042470472 @default.
- W4307366305 creator A5080764187 @default.
- W4307366305 date "2023-05-17" @default.
- W4307366305 modified "2023-09-30" @default.
- W4307366305 title "CmpCNN: CMP Modeling with Transfer Learning CNN Architecture" @default.
- W4307366305 cites W1484136265 @default.
- W4307366305 cites W1969499388 @default.
- W4307366305 cites W1975308008 @default.
- W4307366305 cites W2027733345 @default.
- W4307366305 cites W2030177846 @default.
- W4307366305 cites W2030939156 @default.
- W4307366305 cites W2073433607 @default.
- W4307366305 cites W2077390848 @default.
- W4307366305 cites W2093333193 @default.
- W4307366305 cites W2127767984 @default.
- W4307366305 cites W2128987514 @default.
- W4307366305 cites W2157042424 @default.
- W4307366305 cites W2165698076 @default.
- W4307366305 cites W2172818226 @default.
- W4307366305 cites W2194775991 @default.
- W4307366305 cites W2360470654 @default.
- W4307366305 cites W2800344016 @default.
- W4307366305 cites W2912895282 @default.
- W4307366305 cites W2923996772 @default.
- W4307366305 cites W2935946515 @default.
- W4307366305 cites W2947292684 @default.
- W4307366305 cites W2963163009 @default.
- W4307366305 cites W2964309037 @default.
- W4307366305 cites W2998169401 @default.
- W4307366305 cites W3010776687 @default.
- W4307366305 cites W3011852629 @default.
- W4307366305 cites W3014404070 @default.
- W4307366305 cites W3027658987 @default.
- W4307366305 cites W3035631098 @default.
- W4307366305 cites W3043787075 @default.
- W4307366305 cites W3086794567 @default.
- W4307366305 cites W3092618035 @default.
- W4307366305 cites W3103635814 @default.
- W4307366305 cites W3139332747 @default.
- W4307366305 cites W3160865949 @default.
- W4307366305 cites W3169517138 @default.
- W4307366305 cites W3211956870 @default.
- W4307366305 cites W4213282001 @default.
- W4307366305 cites W4214767096 @default.
- W4307366305 doi "https://doi.org/10.1145/3569941" @default.
- W4307366305 hasPublicationYear "2023" @default.
- W4307366305 type Work @default.
- W4307366305 citedByCount "0" @default.
- W4307366305 crossrefType "journal-article" @default.
- W4307366305 hasAuthorship W4307366305A5002688054 @default.
- W4307366305 hasAuthorship W4307366305A5009236768 @default.
- W4307366305 hasAuthorship W4307366305A5025851882 @default.
- W4307366305 hasAuthorship W4307366305A5042470472 @default.
- W4307366305 hasAuthorship W4307366305A5080764187 @default.
- W4307366305 hasBestOaLocation W43073663051 @default.
- W4307366305 hasConcept C105795698 @default.
- W4307366305 hasConcept C108583219 @default.
- W4307366305 hasConcept C111335779 @default.
- W4307366305 hasConcept C111919701 @default.
- W4307366305 hasConcept C113775141 @default.
- W4307366305 hasConcept C11413529 @default.
- W4307366305 hasConcept C139945424 @default.
- W4307366305 hasConcept C150899416 @default.
- W4307366305 hasConcept C154945302 @default.
- W4307366305 hasConcept C162324750 @default.
- W4307366305 hasConcept C173608175 @default.
- W4307366305 hasConcept C178790620 @default.
- W4307366305 hasConcept C180088628 @default.
- W4307366305 hasConcept C185592680 @default.
- W4307366305 hasConcept C188817802 @default.
- W4307366305 hasConcept C2524010 @default.
- W4307366305 hasConcept C2777303404 @default.
- W4307366305 hasConcept C2779227376 @default.
- W4307366305 hasConcept C33923547 @default.
- W4307366305 hasConcept C41008148 @default.
- W4307366305 hasConcept C48372109 @default.
- W4307366305 hasConcept C50522688 @default.
- W4307366305 hasConcept C530198007 @default.
- W4307366305 hasConcept C68339613 @default.
- W4307366305 hasConcept C81363708 @default.
- W4307366305 hasConcept C94375191 @default.
- W4307366305 hasConcept C98045186 @default.
- W4307366305 hasConceptScore W4307366305C105795698 @default.
- W4307366305 hasConceptScore W4307366305C108583219 @default.
- W4307366305 hasConceptScore W4307366305C111335779 @default.
- W4307366305 hasConceptScore W4307366305C111919701 @default.
- W4307366305 hasConceptScore W4307366305C113775141 @default.
- W4307366305 hasConceptScore W4307366305C11413529 @default.
- W4307366305 hasConceptScore W4307366305C139945424 @default.
- W4307366305 hasConceptScore W4307366305C150899416 @default.
- W4307366305 hasConceptScore W4307366305C154945302 @default.
- W4307366305 hasConceptScore W4307366305C162324750 @default.
- W4307366305 hasConceptScore W4307366305C173608175 @default.