Applied Materials Israel Limited

Efrat Rosenman

Idan Kaizerman

Boaz Cohen

Amit Batikoff

Moshe Rosenweig

Leonid Karlinsky

Daniel Ravid

Assaf Asbag

Orly Zvitia

Yehuda Cohen

Gadi Greenberg

Doron Meshulach

Shimon Levi

Kobi Kan

Erez Ravid

Jeong Ho Yeo

A computerized system and method of training a deep neural network (DNN) is provided. The DNN is trained in a first training cycle using a first training set including first training samples. Each first training sample includes at least one first training image synthetically generated based on design data. Upon receiving a user feedback with respect to the DNN trained using the first training set, a second training cycle is adjusted based on the user feedback by obtaining a second training set including augmented training samples. The DNN is re-trained using the second training set. The augmented training samples are obtained by augmenting at least part of the first training samples using defect-related synthetic data. The trained DNN is usable for examination of a semiconductor specimen.

Method of deep learning-based examination of a semiconductor specimen and system thereof

There are provided system and method of classifying defects in a specimen. The method includes: obtaining one or more defect clusters detected on a defect map of the specimen, each cluster characterized by a set of cluster attributes comprising spatial attributes including spatial density indicative of density of defects in one or more regions accommodating the cluster, each given defect cluster being detected at least based on the spatial density thereof meeting a criterion. The defect map also comprises non-clustered defects. Defects of interest (DOI) are identified in each cluster by performing respective defect filtrations for each cluster and non-clustered defects.

Method of defect classification and system thereof

There are provided system and method of classifying defects in a semiconductor specimen. The method comprises: upon obtaining by a computer a Deep Neural Network (DNN) trained to provide classification-related attributes enabling minimal defect classification error, processing a fabrication process (FP) sample using the obtained trained DNN; and, resulting from the processing, obtaining by the computer classification-related attributes characterizing the at least one defect to be classified, thereby enabling automated classification, in accordance with the obtained classification-related attributes, of the at least one defect presented in the FP image. The DNN is trained using a classification training set comprising a plurality of first training samples and ground truth data associated therewith, each first training sample comprising a training image presenting at least one defect and the ground truth data is informative of classes and/or class distribution of defects presented in the respective first training samples; the FP sample comprises a FP image presenting at least one defect to be classified.

There are provided system and method of examining a semiconductor specimen. The method comprises: upon obtaining a Deep Neural Network (DNN) trained for a given examination-related application within a semiconductor fabrication process, processing together one or more fabrication process (FP) images using the obtained trained DNN, wherein the DNN is trained using a training set comprising ground truth data specific for the given application; and obtaining examination-related data specific for the given application and characterizing at least one of the processed one or more FP images. The examination-related application can be, for example, classifying at least one defect presented by at least one FP image, segmenting the at least one FP image, detecting defects in the specimen presented by the at least one FP image, registering between at least two FP images, regression application enabling reconstructing the at least one FP image in correspondence with different examination modality, etc.

There are provided system and method of segmentation a fabrication process (FP) image obtained in a fabrication of a semiconductor specimen. The method comprises: upon obtaining a Deep Neural Network (DNN) trained to provide segmentation-related data, processing a fabrication process (FP) sample using the obtained trained DNN and, resulting from the processing, obtaining by the computer segments-related data characterizing the FP image to be segmented, the obtained segments-related data usable for automated examination of the semiconductor specimen. The DNN is trained using a segmentation training set comprising a plurality of first training samples and ground truth data associated therewith, each first training sample comprises a training image; FP sample comprises the FP image to be segmented.

There are provided system and method of classifying defects in a specimen. The method includes: obtaining one or more defect clusters detected on a defect map of the specimen, each cluster characterized by a set of cluster attributes comprising spatial attributes including spatial density indicative of density of defects in one or more regions accommodating the cluster, each given defect cluster being detected at least based on the spatial density thereof meeting a criterion; for each cluster, applying a cluster classifier to a respective set of cluster attributes thereof to associate the cluster with one or more labels of a predefined set of labels, wherein the cluster classifier is trained using cluster training data; and identifying DOI in each cluster by performing a defect filtration for each cluster using one or more filtering parameters specified in accordance with the label of the cluster.

A method for characterizing a surface of a sample object, the method including dividing the surface into pixels which are characterized by a parameter variation, and defining blocks of the surface as respective groups of the pixels. The method further includes irradiating the pixels in multiple scans over the surface with radiation having different, respective types of polarization, and detecting returning radiation from the pixels in response to each of the scans. For each scan, respective block signatures of the blocks are constructed, in response to the returning radiation from the group of pixels in each block. Also for each scan, a block signature variation using the respective block signatures of the blocks is determined. In response to the block signature variation, one or more of the types of polarization for use in subsequent examination of a test object are selected.

Growing community of inventors

Aseret, Israel

Efrat Rosenman