One variation of a method for monitoring manufacture of assembly units includes: receiving selection of a target location hypothesized by a user to contain an origin of a defect in assembly units of an assembly type; accessing a feature map linking non-visual manufacturing features to physical locations within the assembly type; for each assembly unit, accessing an inspection image of the assembly unit recorded by an optical inspection station during production of the assembly unit, projecting the target location onto the inspection image, detecting visual features proximal the target location within the inspection image, and aggregating non-visual manufacturing features associated with locations proximal the target location and representing manufacturing inputs into the assembly unit based on the feature map; and calculating correlations between visual and non-visual manufacturing features associated with locations proximal the target location and the defect for the set of assembly units.

A computer-implemented method for training a neural network. The training includes: determining a first feature map by the neural network based on a first transformed image, the first transformed image being determined based on a first transformation of a training image; determining a second feature map by the neural network based on a second transformed image, the second transformed image being determined based on a second transformation of the training image; determining a first loss value characterizing a metric between a first feature vector of the first feature map and a weighted sum of second feature vectors of the second feature map, weights of the weighted sum being determined according to overlaps of a part of the training image characterized by the first feature vector with respect to parts of the training image characterized by the respective second feature vectors; training the neural network based on the first loss value.

A computer-implemented method for training a neural network. The training includes: determining a first feature map by the neural network based on a first transformed image, the first transformed image being determined based on a first transformation of a training image; determining a second feature map by the neural network based on a second transformed image, the second transformed image being determined based on a second transformation of the training image; determining a first loss value characterizing a metric between a first feature vector of the first feature map and a weighted sum of second feature vectors of the second feature map, weights of the weighted sum being determined according to overlaps of a part of the training image characterized by the first feature vector with respect to parts of the training image characterized by the respective second feature vectors; training the neural network based on the first loss value.

In an aspect, the present disclosure provides a method of generating scale selective training data for use in training a machine learning system to support scale selective image classification tasks, comprising obtaining a plurality of images comprising an object of interest at a plurality of image scales; assigning a desired label to each of the plurality of images based on an image scale of the object of interest in the each image, wherein the desired label comprises an in-scope response when the image scale comprises an in-scope image scale, and generating a set of training data for use in training the machine learning system to predict a scale of the object of interest, the training data comprising the plurality of images and corresponding desired labels.

In an aspect, the present disclosure provides a method of generating scale selective training data for use in training a machine learning system to support scale selective image classification tasks, comprising obtaining a plurality of images comprising an object of interest at a plurality of image scales; assigning a desired label to each of the plurality of images based on an image scale of the object of interest in the each image, wherein the desired label comprises an in-scope response when the image scale comprises an in-scope image scale, and generating a set of training data for use in training the machine learning system to predict a scale of the object of interest, the training data comprising the plurality of images and corresponding desired labels.

Systems and methods for processing and using sensor data. The methods comprise: obtaining semantic labels assigned to data points; performing a supervised machine learning algorithm and an unsupervised machine learning algorithm to respectively generate a first confidence score and a second confidence score for each semantic label of said semantic labels, the first and second confidence scores each representing a degree of confidence that the semantic label is correctly assigned to a respective one of the data points; generating a final confidence score for each said semantic label based on the first and second confidence scores; selecting subsets of the data points based on the final confidence scores; and aggregating the data points of the subsets to produce an aggregate set of data points.

Presented herein are systems and methods for classifying features from biomedical images. A computing system may identify a first portion corresponding to an ROI in a first biomedical image derived from a sample. The ROI of the first biomedical image may correspond to a feature of the sample. The computing system may generate a first embedding vector using the first portion of the first biomedical image. The computing system may apply the first embedding vector to a clustering model. The clustering model may have a feature space to define a plurality of conditions. The clustering model may be trained using a second embedding vectors generated from a corresponding second portions with at least one of a plurality of image transformation. The computing system may determine a condition for the feature based on applying the first embedding vector to the clustering model.

Presented herein are systems and methods for classifying features from biomedical images. A computing system may identify a first portion corresponding to an ROI in a first biomedical image derived from a sample. The ROI of the first biomedical image may correspond to a feature of the sample. The computing system may generate a first embedding vector using the first portion of the first biomedical image. The computing system may apply the first embedding vector to a clustering model. The clustering model may have a feature space to define a plurality of conditions. The clustering model may be trained using a second embedding vectors generated from a corresponding second portions with at least one of a plurality of image transformation. The computing system may determine a condition for the feature based on applying the first embedding vector to the clustering model.

Techniques are disclosed for automatically generating new content using a trained 1-to-N generative adversarial network (GAN) model. In disclosed techniques, a computer system receives, from a computing device, a request for newly-generated content, where the request includes current content. The computer system automatically generates, using the trained 1-to-N GAN model, N different versions of new content, where a given version of new content is automatically generated based on the current content and one of N different style codes, where the value of N is at least two. After generating the N different versions of new content, the computer system transmits them to the computing device. The disclosed techniques may advantageously automate a content generation process, thereby saving time and computing resources via execution of the 1-to-N GAN machine learning model.

Techniques are disclosed for automatically generating new content using a trained 1-to-N generative adversarial network (GAN) model. In disclosed techniques, a computer system receives, from a computing device, a request for newly-generated content, where the request includes current content. The computer system automatically generates, using the trained 1-to-N GAN model, N different versions of new content, where a given version of new content is automatically generated based on the current content and one of N different style codes, where the value of N is at least two. After generating the N different versions of new content, the computer system transmits them to the computing device. The disclosed techniques may advantageously automate a content generation process, thereby saving time and computing resources via execution of the 1-to-N GAN machine learning model.