Deep generative models for optical or other mode selection
Abstract:
Methods and systems for selecting a mode of a tool used for a process performed on a specimen are provided. One system includes one or more computer subsystems and one or more components executed by the one or more computer subsystems. The one or more components include a generative adversarial network (GAN), e.g., a conditional GAN (cGAN). The computer subsystem(s) are configured for modifying a portion of design data for a specimen to generate an artificially defective portion of the design data and generating simulated images for the specimen by inputting the portion of the design data and the artificially defective portion of the design data into the GAN. The computer subsystem(s) are also configured for determining one or more characteristics of the simulated images and selecting a mode of a tool used for a process performed on the specimen based on the determined one or more characteristics.
Public/Granted literature
Information query
Patent Agency Ranking
0/0