US 12,360,461 B2
Identification of hot spots or defects by machine learning
Jing Su, Fremont, CA (US); Yi Zou, Foster City, CA (US); Chenxi Lin, Newark, CA (US); Stefan Hunsche, Santa Clara, CA (US); Marinus Jochemsen, Veldhoven (NL); Yen-Wen Lu, Saratoga, CA (US); and Lin Lee Cheong, San Jose, CA (US)
Assigned to ASML NETHERLANDS B.V., Veldhoven (NL)
Filed by ASML NETHERLANDS B.V., Veldhoven (NL)
Filed on May 13, 2022, as Appl. No. 17/744,091.
Application 17/744,091 is a continuation of application No. 16/300,380, granted, now 11,443,083, previously published as PCT/EP2017/059328, filed on Apr. 20, 2017.
Claims priority of provisional application 62/335,544, filed on May 12, 2016.
Prior Publication US 2022/0277116 A1, Sep. 1, 2022
Int. Cl. G06T 7/00 (2017.01); G03F 7/00 (2006.01); G06F 18/28 (2023.01); G06F 30/20 (2020.01); G06F 30/398 (2020.01); G06N 20/00 (2019.01); G06V 10/772 (2022.01)
CPC G03F 7/705 (2013.01) [G03F 7/70525 (2013.01); G06F 18/28 (2023.01); G06F 30/20 (2020.01); G06F 30/398 (2020.01); G06N 20/00 (2019.01); G06T 7/0004 (2013.01); G06V 10/772 (2022.01); G06T 2207/20081 (2013.01); G06T 2207/30148 (2013.01); G06V 2201/06 (2022.01)] 20 Claims
OG exemplary drawing
 
1. A method comprising:
obtaining a characteristic representing how a test pattern performs in terms of being made in a device manufacturing process;
determining based on the characteristic whether the test pattern is a hot spot;
training, by a hardware computer system, a machine learning model using a training set comprising a sample whose feature vector comprises the characteristic and whose label is whether the test pattern is a hot spot; and configuring the device manufacturing process based on the trained machine learning model and/or providing a signal representing, or based on, the trained machine learned model to an apparatus for use by a tool or system in configuring the device manufacturing process.