Kla Tencor Corporation

Infinera Corporation

Kla Corporation

Kla Instruments Corporation

Kla-tencor Technologies Corporation

Scott Allen Young

Kris Bhaskar

Mohan Mahadevan

Tao-Yi Fu

Christopher R Fairley

Guoheng Zhao

Mark Armstrong McCord

Bin-Ming Benjamin Tsai

Lena Nicolaides

Jing Zhang

Richard R Simmons

Bjorn Brauer

Ashok V Kulkarni

Brian Duffy

Eliezer Rosengaus

Alex Salnik

Laurent Karsenti

Doug Keith Masnaghetti

Rainer Knippelmeyer

Neeraj Khanna

Mehdi Vaez-Iravani

Ady Levy

Donald Francis Specht

Ting-Kuang Chiang

Christopher Sears

Fred E Stanke

Richard Wallingford

Edward Everett Sprague

Wayne McMillan

Douglas K Masnaghetti

Grace Hsiu-Ling Chen

Mark J Roulo

Curt H Chadwick

Keith B Wells

Nanchang Zhu

Sankar Venkataraman

Thanh Huy Ha

Aviv Balan

Tjandra Trisno

Daniel L Cavan

Li He

Andy Hill

Huajun Ying

Yale Zhang

Tim S Wihl

Vijay Ramachandran

Dominic David

Fred E Babian

Marco Guevremont

Hung Nien

Bin-Ming Benjanim Tsai

Kent E Douglas

Nicholas Szabo

Roger Kroeze

James J Hager, Jr

Matthew B Lutzker

Methods and systems for determining information for a specimen are provided. Certain embodiments relate to bump height 3D inspection and metrology using deep learning artificial intelligence. For example, one embodiment includes a deep learning (DL) model configured for predicting height of one or more 3D structures formed on a specimen based on one or more images of the specimen generated by an imaging subsystem. One or more computer systems are configured for determining information for the specimen based on the predicted height. Determining the information may include, for example, determining if any of the 3D structures are defective based on the predicted height. In another example, the information determined for the specimen may include an average height metric for the one or more 3D structures.

3D structure inspection or metrology using deep learning

Methods and systems for accelerated training of a machine learning based model for semiconductor applications are provided. One method for training a machine learning based model includes acquiring information for non-nominal instances of specimen(s) on which a process is performed. The machine learning based model is configured for performing simulation(s) for the specimens. The machine learning based model is trained with only information for nominal instances of additional specimen(s). The method also includes re-training the machine learning based model with the information for the non-nominal instances of the specimen(s) thereby performing transfer learning of the information for the non-nominal instances of the specimen(s) to the machine learning based model.

Accelerated training of a machine learning based model for semiconductor applications

A scanning electron microscopy system is disclosed. The system includes a multi-beam scanning electron microscopy (SEM) sub-system. The SEM sub-system includes a multi-beam electron source configured to form a plurality of electron beams, a sample stage configured to secure a sample, an electron-optical assembly to direct the electron beams onto a portion of the sample, and a detector assembly configured to simultaneously acquire multiple images of the surface of the sample. The system includes a controller configured to receive the images from the detector assembly, identify a best focus image of images by analyzing one or more image quality parameters of the images, and direct the multi-lens array to adjust a focus of one or more electron beams based on a focus of an electron beam corresponding with the identified best focus image.

Method and system for focus adjustment of a multi-beam scanning electron microscopy system

Methods and systems for aligning images for a specimen acquired with different modalities are provided. One method includes acquiring information for a specimen that includes at least first and second images for the specimen. The first image is acquired with a first modality different than a second modality used to acquire the second image. The method also includes inputting the information into a learning based model. The learning based model is included in one or more components executed by one or more computer systems. The learning based model is configured for transforming one or more of the at least first and second images to thereby render the at least the first and second images into a common space. In addition, the method includes aligning the at least the first and second images using results of the transforming. The method may also include generating an alignment metric using a classifier.

Learning based approach for aligning images acquired with different modalities

Disclosed are methods and apparatus for detecting defects or reviewing defects in a semiconductor sample. The system has a brightfield (BF) module for directing a BF illumination beam onto a sample and detecting an output beam reflected from the sample in response to the BF illumination beam. The system has a modulated optical reflectance (MOR) module for directing a pump and probe beam to the sample and detecting a MOR output beam from the probe spot in response to the pump beam and the probe beam. The system includes a processor for analyzing the BF output beam from a plurality of BF spots to detect defects on a surface or near the surface of the sample and analyzing the MOR output beam from a plurality of probe spots to detect defects that are below the surface of the sample.

Apparatus and methods for combined brightfield, darkfield, and photothermal inspection

Systems and methods for providing an augmented input data to a convolutional neural network (CNN) are disclosed. Wafer images are received at a processor. The wafer image is divided into a plurality of references images each associated with a die in the wafer image. Test images are received. A plurality of difference images are created by differences the test images with the reference images. The reference images and difference images are assembled into the augmented input data for the CNN and provided to the CNN.

Data augmentation for convolutional neural network-based defect inspection

Methods and systems for performing one or more functions for a specimen using output simulated for the specimen are provided. One system includes one or more computer subsystems configured for acquiring output generated for a specimen by one or more detectors included in a tool configured to perform a process on the specimen. The system also includes one or more components executed by the one or more computer subsystems. The one or more components include a learning based model configured for performing one or more first functions using the acquired output as input to thereby generate simulated output for the specimen. The one or more computer subsystems are also configured for performing one or more second functions for the specimen using the simulated output.

Accelerating semiconductor-related computations using learning based models

The disclosure is directed to providing high resolution stereoscopy with extended depth of focus. Wave front coding in optical paths going to a first detector and at least a second detector may be implemented to affect an intermediate set of images. The intermediate set of images may be filtered (i.e. decoded) to produce a filtered set of images with selected resolution and depth of focus properties. A first filtered image and a second filtered image may be substantially simultaneously presented to respective first and second eyes of an observer to further generate an illusion of enhanced depth (i.e. 3D perception).

Stereo extended depth of focus

Hybrid inspectors are provided. One system includes computer subsystem(s) configured for receiving optical based output and electron beam based output generated for a specimen. The computer subsystem(s) include one or more virtual systems configured for performing one or more functions using at least some of the optical based output and the electron beam based output generated for the specimen. The system also includes one or more components executed by the computer subsystem(s), which include one or more models configured for performing one or more simulations for the specimen. The computer subsystem(s) are configured for detecting defects on the specimen based on at least two of the optical based output, the electron beam based output, results of the one or more functions, and results of the one or more simulations.

Hybrid inspectors

A semiconductor wafer inspection system includes a camera and two or more illuminators. The illuminators illuminate a line of the semiconductor wafer in sequence and the camera captures an interleaved image of illuminated lines such that the individual images can be recovered from the interleaved image. The semiconductor wafer can be moved by a conveyor so that adjacent lines can be sequentially illuminated by the illuminators. The camera may include two or more line sensors.

Combined semiconductor metrology system

A dark field inspection system that minimizes the speckle noise due to sample surface roughness can include a plurality of beam shaping paths for generating a composite, focused illumination line on a wafer. Each beam shaping path can illuminate the wafer at an oblique angle. The plurality of beam shaping paths can form a ring illumination. This ring illumination can reduce the speckle effect, thereby improving SNR. An objective lens can capture scattered light from the wafer and an imaging sensor can receive an output of the objective lens. Because the wafer illumination occurs at oblique angles, the objective lens can have a high NA, thereby improving optical resolution of the imaging sensor, and the resulting signal level.

Dark field inspection system with ring illumination

Embodiments of the present disclosure are directed to an electron beam imaging/inspection apparatus having an electron source device to direct flood electrons on a sample immediately before image acquisition or inspection. The apparatus comprises a first device configured to charge a sample in a first mode, wherein the first device includes an electron source configured to provide a flood beam of charged particles to a first area of the sample. The apparatus also comprises a second device configured to generate a primary beam of electrons and characterize an interaction between the primary beam and a second area of the sample within the first area in a second mode. The apparatus is configured to switch from the first mode to the second mode less than 1 second.

Inspection site preparation

The present invention may include an illumination source; a TDI sensor having a plurality of rows of TDI pixels, wherein each of the TDI pixels have a 1:1 aspect ratio; a multicolor filter contacted to the surface of the TDI sensor, wherein the multicolor filter has alternating sections of a first color filter, a second color filter, and at least a third color, wherein adjacent rows of TDI pixels are grouped in order to form a plurality of rows of integrated multicolor pixels; an objective having a first end positioned proximate to the specimen; a second lens configured to focus light from the image path onto the TDI sensor; and an anamorphic optics element configured to magnify an image of the one or more specimens such that the image is magnified by a factor of three along a direction orthogonal to an integrating direction of the TDI sensor.

Digital pathology system

Growing community of inventors

Soquel, CA, United States of America

Scott Allen Young