Fast and Accurate Machine Learning Inverse Lithography Using Physics Based Feature Maps and Specially Designed DCNN

被引：4

作者：

Shi, Xuelong ^{[1
]}

Yan, Yan ^{[1
]}

Zhou, Tao ^{[1
]}

Yu, Xueru ^{[1
]}

Li, Chen ^{[1
]}

Chen, Shoumian ^{[1
]}

Zhao, Yuhang ^{[1
]}

机构：

[1] Shanghai Integrated Circuits R&D Ctr Co Ltd, Shanghai, Peoples R China

来源：

IWAPS 2020: PROCEEDINGS OF 2020 4TH INTERNATIONAL WORKSHOP ON ADVANCED PATTERNING SOLUTIONS (IWAPS) | 2020年

关键词：

Optimal feature maps; inverse lithography technology (ILT); deep convolution neural network (DCNN);

D O I：

10.1109/iwaps51164.2020.9286814

中图分类号：

T [工业技术];

学科分类号：

08 ;

摘要：

To achieve full chip inverse lithography technology (ILT) solution, we proposed a hybrid approach in this study by combining first few physics based feature maps as model input with a specially designed DCNN structure to learn the rigorous ILT algorithm. Our results show that this approach can make machine learning ILT easy, fast and more accurate.

引用

页码：9 / 11

页数：3

共 50 条

[1] Physics based feature vector design: A critical step towards machine learning based inverse lithography
Shi, Xuelong
Zhao, Yuhang
Chen, Shoumian
Li, Chen
OPTICAL MICROLITHOGRAPHY XXXIII, 2021, 11327
[2] Towards a Fast and Accurate EIT Inverse Problem Solver: A Machine Learning Approach
Fernandez-Fuentes, Xose
Mera, David
Gomez, Andres
Vidal-Franco, Ignacio
ELECTRONICS, 2018, 7 (12)
[3] Physics-Based Machine Learning Electroluminescence Models for Fast yet Accurate Solar Cell Characterization
Laot, Erell
Puel, Jean-Baptiste
Guillemoles, Jean-Francois
Ory, Daniel
PROGRESS IN PHOTOVOLTAICS, 2025,
[4] Optimal Feature Vector Design for Machine Learning Based Computational Lithography
Shi, Xuelong
Zhao, YuHang
Chen, Shoumian
Li, Ming
Yuan, Wei
Yao, Leon
Zhao, Wenhao
Xiao, Yanjun
Kang, Xiaohui
Li, Angmar
OPTICAL MICROLITHOGRAPHY XXXII, 2019, 10961
[5] mirkwood: Fast and Accurate SED Modeling Using Machine Learning
Gilda, Sankalp
Lower, Sidney
Narayanan, Desika
ASTROPHYSICAL JOURNAL, 2021, 916 (01):
[6] Efficient generation of accurate mobility maps using machine learning algorithms
Mechergui, Dave
Jayakumar, Paramsothy
JOURNAL OF TERRAMECHANICS, 2020, 88 : 53 - 63
[7] Fast lithography aerial image calculation method based on machine learning
Ma, Xu
Zhao, Xuejiao
Wang, Zhiqiang
Li, Yanqiu
Zhao, Shengjie
Zhang, Lu
APPLIED OPTICS, 2017, 56 (23) : 6485 - 6495
[8] Fast and accurate characterization of magnetorheological elastomers based on machine learning
Ren, Hang
Zhao, Dan
Dong, Li -Qiang
Liu, Shao-Gang
Yang, Jin-Shui
ACTA PHYSICA SINICA, 2024, 73 (16)
[9] Machine-learning techniques for fast and accurate feature localization in holograms of colloidal particles
Hannel, Mark D.
Abdulali, Aidan
O'brien, Michael
Grier, David G.
OPTICS EXPRESS, 2018, 26 (12): : 15221 - 15231
[10] Solving inverse problems in physics by optimizing a discrete loss: Fast and accurate learning without neural networks
Karnakov, Petr
Litvinov, Sergey
Koumoutsakos, Petros
PNAS NEXUS, 2023, 3 (01):

← 1 2 3 4 5 →