Matches in SemOpenAlex for { <https://semopenalex.org/work/W4387567432> ?p ?o ?g. }
Showing items 1 to 91 of
91
with 100 items per page.
- W4387567432 abstract "With the growing demand for semiconductor products, the semiconductor manufacturing industries are trying to increase their production capacities. Additional requirements and constraints are also enforced on semiconductor manufacturing equipment, particularly on robustness for visual inspections and vision-based alignment. Deep neural networks (DNNs) are prominently used for vision-based tasks to improve robustness. The challenge, however, is that semiconductor manufacturing industries still use brownfield systems and equipment with legacy hardware and software. The legacy systems introduce challenging requirements and constraints on the DNN deployment and the traditional approach to inference optimization results in poor inference performance. This paper presents a structured approach to optimize the inference of DNNs for vision-based tasks for industrial brownfield architectures with existing legacy hardware, software, and the associated requirements and constraints. Four directions in the machine learning operations (MLOps) pipeline are explored in this approach - DNN architecture selection, DNN model optimization, target deployment platform, and inference engine - while adhering to the legacy systems’ requirements and constraints. We present our approach using the case study from the semiconductor manufacturing industry that deploys DNNs for vision-based position detection in their legacy equipment. The results of the optimized DNN deployment are compared with a baseline implementation, and up to 44% improvement in inference timing performance is achieved without compromising on inference accuracy." @default.
- W4387567432 created "2023-10-13" @default.
- W4387567432 creator A5026304916 @default.
- W4387567432 creator A5028529557 @default.
- W4387567432 creator A5038997447 @default.
- W4387567432 creator A5049989469 @default.
- W4387567432 creator A5093049275 @default.
- W4387567432 date "2023-09-12" @default.
- W4387567432 modified "2023-10-13" @default.
- W4387567432 title "A Structured Inference Optimization Approach for Vision-Based DNN Deployment on Legacy Systems" @default.
- W4387567432 cites W2076832509 @default.
- W4387567432 cites W2233116163 @default.
- W4387567432 cites W2253367621 @default.
- W4387567432 cites W2743948853 @default.
- W4387567432 cites W2796625795 @default.
- W4387567432 cites W2797932837 @default.
- W4387567432 cites W2963163009 @default.
- W4387567432 cites W2963918968 @default.
- W4387567432 cites W2964081807 @default.
- W4387567432 cites W2992814786 @default.
- W4387567432 cites W3035503061 @default.
- W4387567432 cites W3120894151 @default.
- W4387567432 cites W3187130808 @default.
- W4387567432 cites W4207016755 @default.
- W4387567432 cites W4313180727 @default.
- W4387567432 doi "https://doi.org/10.1109/etfa54631.2023.10275468" @default.
- W4387567432 hasPublicationYear "2023" @default.
- W4387567432 type Work @default.
- W4387567432 citedByCount "0" @default.
- W4387567432 crossrefType "proceedings-article" @default.
- W4387567432 hasAuthorship W4387567432A5026304916 @default.
- W4387567432 hasAuthorship W4387567432A5028529557 @default.
- W4387567432 hasAuthorship W4387567432A5038997447 @default.
- W4387567432 hasAuthorship W4387567432A5049989469 @default.
- W4387567432 hasAuthorship W4387567432A5093049275 @default.
- W4387567432 hasConcept C104317684 @default.
- W4387567432 hasConcept C105339364 @default.
- W4387567432 hasConcept C105446022 @default.
- W4387567432 hasConcept C115903868 @default.
- W4387567432 hasConcept C119599485 @default.
- W4387567432 hasConcept C119857082 @default.
- W4387567432 hasConcept C120314980 @default.
- W4387567432 hasConcept C127413603 @default.
- W4387567432 hasConcept C149635348 @default.
- W4387567432 hasConcept C154945302 @default.
- W4387567432 hasConcept C160671074 @default.
- W4387567432 hasConcept C185592680 @default.
- W4387567432 hasConcept C199360897 @default.
- W4387567432 hasConcept C2776214188 @default.
- W4387567432 hasConcept C2777904410 @default.
- W4387567432 hasConcept C41008148 @default.
- W4387567432 hasConcept C46743427 @default.
- W4387567432 hasConcept C55493867 @default.
- W4387567432 hasConcept C63479239 @default.
- W4387567432 hasConcept C66018809 @default.
- W4387567432 hasConceptScore W4387567432C104317684 @default.
- W4387567432 hasConceptScore W4387567432C105339364 @default.
- W4387567432 hasConceptScore W4387567432C105446022 @default.
- W4387567432 hasConceptScore W4387567432C115903868 @default.
- W4387567432 hasConceptScore W4387567432C119599485 @default.
- W4387567432 hasConceptScore W4387567432C119857082 @default.
- W4387567432 hasConceptScore W4387567432C120314980 @default.
- W4387567432 hasConceptScore W4387567432C127413603 @default.
- W4387567432 hasConceptScore W4387567432C149635348 @default.
- W4387567432 hasConceptScore W4387567432C154945302 @default.
- W4387567432 hasConceptScore W4387567432C160671074 @default.
- W4387567432 hasConceptScore W4387567432C185592680 @default.
- W4387567432 hasConceptScore W4387567432C199360897 @default.
- W4387567432 hasConceptScore W4387567432C2776214188 @default.
- W4387567432 hasConceptScore W4387567432C2777904410 @default.
- W4387567432 hasConceptScore W4387567432C41008148 @default.
- W4387567432 hasConceptScore W4387567432C46743427 @default.
- W4387567432 hasConceptScore W4387567432C55493867 @default.
- W4387567432 hasConceptScore W4387567432C63479239 @default.
- W4387567432 hasConceptScore W4387567432C66018809 @default.
- W4387567432 hasLocation W43875674321 @default.
- W4387567432 hasOpenAccess W4387567432 @default.
- W4387567432 hasPrimaryLocation W43875674321 @default.
- W4387567432 hasRelatedWork W2043719711 @default.
- W4387567432 hasRelatedWork W2057057690 @default.
- W4387567432 hasRelatedWork W2140069467 @default.
- W4387567432 hasRelatedWork W2321443665 @default.
- W4387567432 hasRelatedWork W2358964818 @default.
- W4387567432 hasRelatedWork W2359535128 @default.
- W4387567432 hasRelatedWork W2364072231 @default.
- W4387567432 hasRelatedWork W2368184788 @default.
- W4387567432 hasRelatedWork W2375699995 @default.
- W4387567432 hasRelatedWork W2381332051 @default.
- W4387567432 isParatext "false" @default.
- W4387567432 isRetracted "false" @default.
- W4387567432 workType "article" @default.