Litho-neuralode: Improving hotspot detection accuracy with advanced data augmentation and neural ordinary differential equations

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

7 Scopus citations

Abstract

The use of deep neural networks in pattern matching has tremendously improved the accuracy of the lithographic hotspot detection, preventing any catastrophic chip failure. In this paper, we propose three data augmentation techniques (“Translation”, “Gaussian noise”, and “Fill shapes”) to deal with the imbalance outlier lithographic hotspot problem and adopt the neural ordinary differential equations networks (Litho-NeuralODE) to improve the detection accuracy. Our architecture uses 28×28 pixel clips to perform the hotspot classification. Experimental result on ICCAD 2012 Contest benchmarks shows that our proposed framework achieves the overall highest accuracy of 98.7% and the lowest misses of 10 on average, outperforming the state-of-the-art works.

Original languageEnglish
Title of host publicationGLSVLSI 2020 - Proceedings of the 2020 Great Lakes Symposium on VLSI
PublisherAssociation for Computing Machinery
Pages387-392
Number of pages6
ISBN (Electronic)9781450379441
DOIs
StatePublished - 7 Sep 2020
Externally publishedYes
Event30th Great Lakes Symposium on VLSI, GLSVLSI 2020 - Virtual, Online, China
Duration: 7 Sep 20209 Sep 2020

Publication series

NameProceedings of the ACM Great Lakes Symposium on VLSI, GLSVLSI

Conference

Conference30th Great Lakes Symposium on VLSI, GLSVLSI 2020
Country/TerritoryChina
CityVirtual, Online
Period7/09/209/09/20

Keywords

  • Deep Neural Network
  • Design for Manufacturability
  • Feature Extraction
  • Lithography Hotspot Detection

Fingerprint

Dive into the research topics of 'Litho-neuralode: Improving hotspot detection accuracy with advanced data augmentation and neural ordinary differential equations'. Together they form a unique fingerprint.

Cite this