Applied Materials Israel Limited

Playtika Ltd.

Idan Kaizerman

Efrat Rosenman

Efrat Rozenman

Daniel Ravid

Boaz Cohen

Amit Batikoff

Gadi Greenberg

Assaf Asbag

Moshe Rosenweig

Leonid Karlinsky

Ishai Schwarzband

Yotam Sofer

Saar Shabtay

Orly Zvitia

Ohad Shaubi

Mark Geshel

Amir Wachs

Zeev Zohar

Vladimir Shlain

Yan Ivanchenko

Amir Watchs

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.

Methods and systems for addressing the needs of application users such as players of social games or online games. One of the methods includes: receiving a user request to start a session in gaming software, the user request coming from a first user having a first account, the gaming software configured to provide an offer for a physical product; providing, to the gaming software, an offer for a physical product for display at a specified time by the user interface of the user device, wherein the offer and specified time are determined based at least in part on historical activity of the first account including start times and associated durations of prior gaming software sessions of the first account; detecting a user interaction with the offer for the physical product, and in response to the detection, taking an action in a process of ordering the physical product.

Adaptive in-application physical product offers

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.

Inspection apparatus includes an imaging module, which is configured to capture images of defects at different, respective locations on a sample. A processor is coupled to process the images so as to automatically assign respective classifications to the defects, and to autonomously control the imaging module to continue capturing the images responsively to the assigned classifications.

Closed-loop automatic defect inspection and classification

A system and method for detecting anomalies in gaming patterns, including: obtaining a time series data related to events; extracting event features of the events; calculating a normalized density estimation for each of the events; assigning outlier probability for each of the events based on the normalized density estimation; determining that an event is an outlier event if the outlier probability of the event is above an outlier threshold; calculating, for each window of the time series data, a set of window features based on the outlier events in the window; modeling the window features by a generative model; assigning outlier confidence value for each of the suspected windows based on the distribution of the window features relatively to the generative model; and determining that a window is a suspected window if the outlier confidence value of the window is above a confidence threshold.

System and method for outlier detection in gaming

Data indicative of a group of defect candidates may be obtained. The data may be indicative of a group of defect candidates and may include values of attributes for each defect candidate of the group of defect candidates. Sub-groups of defect candidates may be iteratively selected for review using a review recipe to classify the defect candidates in each selected sub-group based on the values of attributes of respective defect candidates and classification results of previously reviewed defect candidates. The sub-groups may be selected until a sampling stop condition is fulfilled to obtain a classification output for the wafer. Instructions specifying at least one of the sampling stop condition, the inspection recipe, or the review recipe may be altered and additional defect candidates in a next wafer may be classified by using the altered instructions.

Iterative defect filtering process

There is provided a system that includes a review tool configured to review at least part of potential defects of an examined object, and assign each of the at least part of the potential defects with a multiplicity of attribute values. The system also includes a computer-based classifier configured to classify, based on the attribute values as assigned, the at least part of potential defects into a set of classes, the set comprising at least a first major class, a second major class and a first minor class, the classifier trained based on a training set comprising a multiplicity of training defects with assigned attribute values, the training defects classified into the set of classes.

System, method and computer program product for generating a training set for a classifier

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 process analysis includes acquiring first inspection data, using a first inspection modality, with respect to a substrate having multiple instances of a predefined pattern of features formed thereon using different, respective sets of process parameters. Characteristics of defects identified in the first inspection data are processed so as to select a first set of defect locations in which the first inspection data are indicative of an influence of the process parameters on the defects. Second inspection data are acquired, using a second inspection modality having a finer resolution than the first inspection modality, of the substrate at the locations in the first set. The defects appearing in the second inspection data are analyzed so as to select, from within the first set of the locations, a second set of the locations in which the second inspection data are indicative of an optimal range of the process parameters.

Process window analysis

Data indicative of alignment targets may be received. Each alignment target may be associated with a target location on an object. Locations of the object to be inspected may be identified. An alignment target from the alignment targets may be selected. Each of the locations may be within a determined distance from the selected alignment target. An indication may be provided to align the object relative to an examination tool for inspecting the locations within the determined distance from the selected alignment target.

Method of examining locations in a wafer with adjustable navigation accuracy and system thereof

There are provided a system, computer software product and method of generating a training set for a classifier using a processor. The method comprises: receiving a training set comprising training defects each having assigned attribute values, the training defects externally classified into classes comprising first and second major classes and a minor class; training a classifier upon the training set; receiving results of automatic classification of the training defects; automatically identifying a first defect that was externally classified into the first major class and automatically classified into the second major class; automatically identifying by the processor a second defect from the multiplicity of training defects that was externally classified into the minor class and automatically classified to the first or second major classes; and correcting the training set to include the first defect into the second major class, or to include the second defect into the first or the second major class.

Growing community of inventors

Meitar, Israel

Idan Kaizerman