Full metadata record
DC FieldValueLanguage
dc.contributor.authorYu, Yen-Tingen_US
dc.contributor.authorLin, Geng-Heen_US
dc.contributor.authorJiang, Iris Hui-Ruen_US
dc.contributor.authorChiang, Charlesen_US
dc.description.abstractBecause of the widening sub-wavelength lithography gap in advanced fabrication technology, lithography hotspot detection has become an essential task in design for manufacturability. Current state-of-the-art works unite pattern matching and machine learning engines. Unlike them, we fully exploit the strengths of machine learning using novel techniques. By combing topological classification and critical feature extraction, our hotspot detection framework achieves very high accuracy. Furthermore, to speed up the evaluation, we verify only possible layout clips instead of full-layout scanning. After detection, we filter hotspots to reduce the false alarm. Experimental results show that the proposed framework is very accurate and demonstrates a rapid training convergence. Moreover, our framework outperforms the 2012 CAD Contest at ICCAD winner on accuracy and false alarm.en_US
dc.subjectDesign for manufacturabilityen_US
dc.subjectlithography hotspoten_US
dc.subjecthotspot detectionen_US
dc.subjectfuzzy pattern matchingen_US
dc.subjectmachine learningen_US
dc.subjectsupport vector machineen_US
dc.titleMachine-Learning-Based Hotspot Detection Using Topological Classification and Critical Feature Extractionen_US
dc.typeProceedings Paperen_US
dc.identifier.journal2013 50TH ACM / EDAC / IEEE DESIGN AUTOMATION CONFERENCE (DAC)en_US
dc.contributor.departmentDepartment of Electronics Engineering and Institute of Electronicsen_US
Appears in Collections:Conferences Paper