Abstract | ||
---|---|---|
Lithography simulation is computationally expensive for hotspot detection. Machine learning based hotspot detection is a promising technique to reduce the simulation overhead. However, most learning approaches rely on a large amount of training data to achieve good accuracy and generality. At the early stage of developing a new technology node, the amount of data with labeled hotspots or non-hotspots is very limited. In this paper, we propose a semi-supervised hotspot detection with self-paced multi-task learning paradigm, leveraging both data samples w./w.o. labels to improve model accuracy and generality. Experimental results demonstrate that our approach can achieve 2.9--4.5% better accuracy at the same false alarm levels than the state-of-the-art work using 10%-50% of training data. The source code and trained models are released on https://github.com/qwepi/SSL.
|
Year | DOI | Venue |
---|---|---|
2019 | 10.1145/3287624.3287685 | ASP-DAC |
Field | DocType | Citations |
Training set,Multi-task learning,False alarm,Computer science,Source code,Real-time computing,Artificial intelligence,Design for manufacturability,Hotspot (Wi-Fi),Machine learning,Generality | Conference | 3 |
PageRank | References | Authors |
0.42 | 11 | 6 |
Name | Order | Citations | PageRank |
---|---|---|---|
Ying Chen | 1 | 3 | 0.76 |
Yibo Lin | 2 | 119 | 20.98 |
Tianyang Gai | 3 | 4 | 0.76 |
Yajuan Su | 4 | 4 | 1.44 |
Yayi Wei | 5 | 4 | 1.44 |
David Z. Pan | 6 | 2653 | 237.64 |