US 12,288,022 B2
Methods and systems for generating shape data for electronic designs
Suhas Pillai, San Jose, CA (US); Thang Nguyen, San Jose, CA (US); and Ajay Baranwal, Dublin, CA (US)
Assigned to Center for Deep Learning in Electronics Manufacturing, San Jose, CA (US)
Filed by Center for Deep Learning in Electronics Manufacturing, Inc., San Jose, CA (US)
Filed on Oct. 17, 2023, as Appl. No. 18/488,823.
Application 18/488,823 is a continuation of application No. 17/453,321, filed on Nov. 2, 2021, granted, now 11,847,400.
Application 17/453,321 is a continuation of application No. 17/022,363, filed on Sep. 16, 2020, granted, now 11,250,199, issued on Feb. 15, 2022.
Prior Publication US 2024/0046023 A1, Feb. 8, 2024
This patent is subject to a terminal disclaimer.
Int. Cl. G06F 30/30 (2020.01); G03F 7/00 (2006.01); G06F 30/398 (2020.01); G06N 3/045 (2023.01)
CPC G06F 30/398 (2020.01) [G03F 7/705 (2013.01); G06N 3/045 (2023.01)] 21 Claims
OG exemplary drawing
 
1. A system for generation of shape data for a set of electronic designs, the system comprising:
a computer processor configured to receive a set of shape data, wherein the set of shape data represents a set of shapes for a device fabrication process; and
a computer processor configured to determine a set of generated shape data, using a convolutional neural network on the set of shape data, wherein the convolutional neural network comprises a generator trained with a set of pre-determined discriminators;
wherein the set of generated shape data comprises a generated scanning electron microscope (SEM) image; and
wherein each discriminator in the set of pre-determined discriminators handles a different input image size sub-sampled from the generated SEM image.