Physics-Informed Optical Kernel Regression Using Complex-valued Neural Fields

Guojin Chen, Zehua Pei, Haoyu Yang, Yuzhe Ma, Bei Yu, Martin Wong

Research output: Chapter in book/report/conference proceedingConference proceedingpeer-review

10 Citations (Scopus)

Abstract

Lithography is fundamental to integrated circuit fabrication, necessitating large computation overhead. The advancement of machine learning (ML)-based lithography models alleviates the trade-offs between manufacturing process expense and capability. However, all previous methods regard the lithography system as an image-to-image black box mapping, utilizing network parameters to learn by rote mappings from massive mask-to-aerial or mask-to-resist image pairs, resulting in poor generalization capability. In this paper, we propose a new ML-based paradigm disassembling the rigorous lithographic model into non-parametric mask operations and learned optical kernels containing determinant source, pupil, and lithography information. By optimizing complex-valued neural fields to perform optical kernel regression from coordinates, our method can accurately restore lithography system using a small-scale training dataset with fewer parameters, demonstrating superior generalization capability as well. Experiments show that our framework can use 31% of parameters while achieving 69× smaller mean squared error with 1.3× higher throughput than the state-of-the-art.
Original languageEnglish
Title of host publication60th ACM/IEEE Design Automation Conference - Proceedings 2023
PublisherIEEE
Pages1-6
Number of pages6
ISBN (Electronic)9798350323481
ISBN (Print)9798350323498
DOIs
Publication statusPublished - 13 Jul 2023
Event60th ACM/IEEE Design Automation Conference, DAC 2023 - Moscone West, San Francisco, United States
Duration: 9 Jul 202313 Jul 2023
https://www.dac.com/
https://60dac.conference-program.com/
https://ieeexplore.ieee.org/xpl/conhome/10247654/proceeding

Publication series

NameACM/IEEE Design Automation Conference - Proceedings
Volume2023-July
ISSN (Print)0738-100X

Conference

Conference60th ACM/IEEE Design Automation Conference, DAC 2023
Country/TerritoryUnited States
CitySan Francisco
Period9/07/2313/07/23
Internet address

Scopus Subject Areas

  • Electrical and Electronic Engineering
  • Control and Systems Engineering
  • Computer Science Applications
  • Modelling and Simulation

User-Defined Keywords

  • Adaptive optics
  • Lithography
  • Optical device fabrication
  • Optical imaging
  • Resists
  • Throughput
  • Training

Fingerprint

Dive into the research topics of 'Physics-Informed Optical Kernel Regression Using Complex-valued Neural Fields'. Together they form a unique fingerprint.

Cite this