DEEP LEARNING FOR SEMANTIC SEGMENTATION OF PATTERN

A method for training a deep learning model of a patterning process. The method includes obtaining (i) training data comprising an input image of at least a part of a substrate having a plurality of features and a truth image, (ii) a set of classes, each class corresponding to a feature of the plura...

Full description

Saved in:
Bibliographic Details
Main Authors Middlebrooks, Scott Anderson, Kiers, Antoine Gaston Marie, Maslow, Mark John, KOOPMAN, Adrianus Cornelis Matheus
Format Patent
LanguageEnglish
Published 13.10.2022
Subjects
APPARATUS SPECIALLY ADAPTED THEREFOR
CALCULATING
CINEMATOGRAPHY
COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
COMPUTING
COUNTING
ELECTROGRAPHY
HOLOGRAPHY
IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
MATERIALS THEREFOR
ORIGINALS THEREFOR
PHOTOGRAPHY
PHOTOMECHANICAL PRODUCTION OF TEXTURED OR PATTERNED SURFACES,e.g. FOR PRINTING, FOR PROCESSING OF SEMICONDUCTORDEVICES
PHYSICS
Online AccessGet full text

Cover

More Information
Summary:A method for training a deep learning model of a patterning process. The method includes obtaining (i) training data comprising an input image of at least a part of a substrate having a plurality of features and a truth image, (ii) a set of classes, each class corresponding to a feature of the plurality of features of the substrate within the input image, and (iii) a deep learning model configured to receive the training data and the set of classes, generating a predicted image, by modeling and/or simulation of the deep learning model using the input image, assigning a class of the set of classes to a feature within the predicted image based on matching of the feature with a corresponding feature within the truth image, and generating, by modeling and/or simulation, a trained deep learning model by iteratively assigning weights using a loss function.
Bibliography:Application Number: US202217837096