Can I read Litho-NeuralODE: Improving Hotspot Detection Accuracy with Advanced Data Augmentation and Neural Ordinary Differential Equations on EtoBox?

Litho-NeuralODE: Improving Hotspot Detection Accuracy with Advanced Data Augmentation and Neural Ordinary Differential Equations by Lu, Wei ;Zhang, Yuhang ;Zhang, Qing ;Zhang, Xinjie ;Li, Yongfu is a scholarly article available to read on EtoBox.

What is Litho-NeuralODE: Improving Hotspot Detection Accuracy with Advanced Data Augmentation and Neural Ordinary Differential Equations about?

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. ## CCS CONCEPTS • Hardware → Physical synthesis.

Author

Lu, Wei ;Zhang, Yuhang ;Zhang, Qing ;Zhang, Xinjie ;Li, Yongfu

Publisher

ACM

Published

2020

Language

EN