Thursday, May 2025

05:00 PM - 08:00 PM

Room: 220A

Session: Artificial Intelligence Including Machine Learning for Imaging Posters

Practical Lithography Prediction System with AI model

Description:

Computational lithography and recently proposed deep learning methods face several practical issues in real-world applications. We propose a system that implementing data collection, data alignment, training, and model evaluation that can be utilized in actual mask design procedure. On real mask images datasets, our method achieves 90.6% Mean Intersection over Union between predicted and real CD-SEM images with a speed of 2.5 ms per image. Our method demonstrates strong competitiveness.