Abstract: Embodiments may include methods, systems, and apparatuses for care area based swath speed for throughput and sensitivity improvement. A method may comprise receiving scan region of a die. The scan region of the die may have a first care area at a controller configured to control an inspection tool, wherein the inspection tool includes a stage having the die disposed thereon. The method may then include scanning a first portion of the scan region at a fast feed rate and the first care area at a slow feed rate. Scanning may include emitting particles in a particle beam toward the die resulting an incidence on the die. Emitting may be performed using a particle emitter. Scanning may then include detecting a portion of particles reflected from the incidence. Detecting may be performed using a detector. Scanning may then include changing a position of the stage relative to the incidence.

Abstract: Embodiments disclosed herein may comprise receiving a run-time image of a run-time die and, with a deep learning module, identifying a characteristic noise in the run-time image, and modifying the run-time image to reduce the characteristic noise, thereby generating a de-noised run-time image. Such embodiments may be performed as methods, by systems, or from non-transitory computer-readable storage media on one or more computing devices. An image sensor of a metrology tool may capture the run-time image of the run-time die. The metrology tool may include a run-time die disposed on a specimen, a run-time image sensor, and a processor in electronic communication with the run-time image sensor. Embodiments may further comprise receiving a training image of a training die, modifying the training image, and training the deep learning module to identify the characteristic noise in the run-time image and modify the run-time image.

Abstract: A device design file and material properties are inputted into a neural network module configured to operate a generative adversarial network. A process parameter is determined based on a device design file and material properties inputs using the generative adversarial network. This can be used to provide process parameters during semiconductor device design or manufacturing.

Abstract: A system for analyzing a sample includes an inspection sub-system and at least one controller. The inspection sub-system is configured to scan a sample to collect a first plurality of sample images having a first image resolution. The controller is configured to generate a defect list based on the first plurality of sample images. The controller is further configured to input images corresponding to the defect list into a neural network that is trained with source data including sample images having the first image resolution and sample images having a second image resolution higher than the first image resolution. The controller is further configured to generate a second plurality of sample images with the neural network based on the images corresponding to the defect list, where the second plurality of sample images have the second image resolution and correspond to the defect list.

Abstract: Embodiments disclosed herein may comprise receiving a run-time image of a run-time die and, with a deep learning module, identifying a characteristic noise in the run-time image, and modifying the run-time image to reduce the characteristic noise, thereby generating a de-noised run-time image. Such embodiments may be performed as methods, by systems, or from non-transitory computer-readable storage media on one or more computing devices. An image sensor of a metrology tool may capture the run-time image of the run-time die. The metrology tool may include a run-time die disposed on a specimen, a run-time image sensor, and a processor in electronic communication with the run-time image sensor. Embodiments may further comprise receiving a training image of a training die, modifying the training image, and training the deep learning module to identify the characteristic noise in the run-time image and modify the run-time image.

Abstract: Embodiments may include methods, systems, and apparatuses for care area based swath speed for throughput and sensitivity improvement. A method may comprise receiving scan region of a die. The scan region of the die may have a first care area at a controller configured to control an inspection tool, wherein the inspection tool includes a stage having the die disposed thereon. The method may then include scanning a first portion of the scan region at a fast feed rate and the first care area at a slow feed rate. Scanning may include emitting particles in a particle beam toward the die resulting an incidence on the die. Emitting may be performed using a particle emitter. Scanning may then include detecting a portion of particles reflected from the incidence. Detecting may be performed using a detector. Scanning may then include changing a position of the stage relative to the incidence.

Abstract: A system for analyzing a sample includes an inspection sub-system and at least one controller. The inspection sub-system is configured to scan a sample to collect a first plurality of sample images having a first image resolution. The controller is configured to generate a defect list based on the first plurality of sample images. The controller is further configured to input images corresponding to the defect list into a neural network that is trained with source data including sample images having the first image resolution and sample images having a second image resolution higher than the first image resolution. The controller is further configured to generate a second plurality of sample images with the neural network based on the images corresponding to the defect list, where the second plurality of sample images have the second image resolution and correspond to the defect list.