Kla Tencor Corporation

Kla Corporation

Marvell International Limited

Marvellworld Trade Ltd.

Erfan Soltanmohammadi

Martin Plihal

Prasanti Uppaluri

Kapil Jain

Saravanan Paramasivam

Chris Maher

Ankit Jain

Sairam Ravu

Mohit Jani

Bjorn Brauer

Brian Duffy

Hucheng Lee

Sangbong Park

Santosh Bhattacharyya

Gordon Rouse

Boshi Huang

Vijay Ramachandran

Vladimir Tumakov

Tai-Kam Ng

Sarath Shekkizhar

Christopher Painter

Ashwin Ramakrishnan

Sang Hyun Lee

A care area is determined in an image of a semiconductor wafer. The care area is divided into sub-care areas based on the shapes of polygons in a design file associated with the care area. A noise scan of a histogram for the sub-care areas is then performed. The sub-care areas are clustered into groups based on the noise scan of the histogram.

Clustering sub-care areas based on noise characteristics

An inspection system may receive inspection datasets from a defect inspection system associated with inspection of one or more samples, where an inspection dataset of the plurality of inspection datasets associated with a defect includes values of two or more signal attributes and values of one or more context attributes. An inspection system may further label each of the inspection datasets with a class label based on respective positions of each of the inspection datasets in a signal space defined by the two or more signal attributes, where each class label corresponds to a region of the signal space. An inspection system may further segment the inspection datasets into two or more defect groups by training a classifier with the values of the context attributes and corresponding class labels for the inspection datasets, where the two or more defect groups are identified based on the trained classifier.

Unsupervised defect segmentation

Wafer inspection with stable nuisance rates and defect of interest capture rates are disclosed. This technique can be used for discovery of newly appearing defects that occur during the manufacturing process. Based on a first wafer, defects of interest are identified based on the classified filtered inspection results. For each remaining wafer, the defect classifier is updated and defects of interest in the next wafer are identified based on the classified filtered inspection results.

Diagnostic methods for the classifiers and the defects captured by optical tools

Systems and methods for detecting defect candidates on a specimen are provided. One method includes, after scanning of at least a majority of a specimen is completed, applying one or more segmentation methods to at least a substantial portion of output generated during the scanning thereby generating two or more segments of the output. The method also includes separately detecting outliers in the two or more segments of the output. In addition, the method includes detecting defect candidates on the specimen by applying one or more predetermined criteria to results of the separately detecting to thereby designate a portion of the detected outliers as the defect candidates.

Defect candidate generation for inspection

Defects of interest can be captured by a classifier. Images of a semiconductor wafer can be received at a deep learning classification module. These images can be sorted into soft decisions with the deep learning classification module. A class of the defect of interest for an image can be determined from the soft decisions. The deep learning classification module can be in electronic communication with an optical inspection system or other types of semiconductor inspection systems.

Creating and tuning a classifier to capture more defects of interest during inspection

Methods and systems for setting up inspection of a specimen with design and noise based care areas are provided. One system includes one or more computer subsystems configured for generating a design-based care area for a specimen. The computer subsystem(s) are also configured for determining one or more output attributes for multiple instances of the care area on the specimen, and the one or more output attributes are determined from output generated by an output acquisition subsystem for the multiple instances. The computer subsystem(s) are further configured for separating the multiple instances of the care area on the specimen into different care area sub-groups such that the different care area sub-groups have statistically different values of the output attribute(s) and selecting a parameter of an inspection recipe for the specimen based on the different care area sub-groups.

And noise based care areas

Methods and systems for training an inspection-related algorithm are provided. One system includes one or more computer subsystems configured for performing an initial training of an inspection-related algorithm with a labeled set of defects thereby generating an initial version of the inspection-related algorithm and applying the initial version of the inspection-related algorithm to an unlabeled set of defects. The computer subsystem(s) are also configured for altering the labeled set of defects based on results of the applying. The computer subsystem(s) may then iteratively re-train the inspection-related algorithm and alter the labeled set of defects until one or more differences between results produced by a most recent version and a previous version of the algorithm meet one or more criteria. When the one or more differences meet the one or more criteria, the most recent version of the inspection-related algorithm is outputted as the trained algorithm.

Optimizing training sets used for setting up inspection-related algorithms

An audio processing circuit comprises an analyzer circuit that includes a plurality of energy detector units, and an equalizer circuit that includes a plurality of equalization filters. The equalizer circuit is coupled with the analyzer circuit. The analyzer circuit is configured to receive an audio signal, obtain sub-bands of the audio signal using the energy detector units, measure energy of each sub-band, compare the energy of each sub-band to a threshold energy value and, based on the comparison, determine parameters for an equalization filter for processing the sub-band. The equalizer circuit is configured to receive the audio signal concurrently with reception of the audio signal by the analyzer circuit, obtain the sub-bands using the equalization filters, receive the parameters for the equalization filters from the analyzer circuit, equalize each sub-band by applying the parameters corresponding to the sub-band, and generate an output audio signal that includes the equalized sub-bands.

Processing audio signals

Systems, methods, and other embodiments associated with converting an input signal into an output signal with a different sampling rate. In one embodiment, an apparatus includes a feedforward circuit configured to receive the input signal comprised of discrete data samples with the first sampling rate and to generate a first intermediate value based, at least in part, on a feedforward coefficient and the input signal. The apparatus includes a feedback circuit configured to generate a second intermediate value that is based, at least in part, on a feedback coefficient and a predetermined number of previous samples of the output signal. The apparatus includes a signal combiner configured to combine the first intermediate value and the second intermediate value together to interpolate a data sample of the output signal at the second sampling rate. The output signal is a converted form of the input signal at the second sampling rate.

Filter for data rate conversion using feedback with a different frequency

Growing community of inventors

Campbell, CA, United States of America

Erfan Soltanmohammadi