Abstract: A device generates a training set of images by, for each image of a plurality of training images, receiving user input of a set of labels for a portion of the image, the portion less than an entirety of the image, the set of labels comprising classifications of individual pixels within the image, and automatically applying a label of unknown to a remainder of the image that excludes the portion of the image. The device inputs an unlabeled image into a machine learning model, the machine learning model trained using the training set, and receives, as output from the machine learning model, predicted classifications for each pixel of the image.

Abstract: A model management system adaptively refines a training dataset for more effective visual inspection. The system trains a machine learning model using the initial training dataset and sends the trained model to a client for deployment. The deployment process generates outputs that are sent back to the system. The system determines that performance of predictions for noisy data points are inadequate and determines a cause of failure based on a mapping of the noisy data point to a distribution generated for the training dataset across multiple dimensions. The system determines a cause of failure based on an attribute of the noisy datapoint that deviates from the distribution of the training dataset and performs refinement towards the training dataset based on the identified cause of failure. The system retrains the machine learning model with the refined training dataset and sends the retrained machine learning model back to the client for re-deployment.

Abstract: A model management system adaptively refines a training dataset for more effective visual inspection. The system trains a machine learning model using the initial training dataset and sends the trained model to a client for deployment. The deployment process generates outputs that are sent back to the system. The system determines that performance of predictions for noisy data points are inadequate and determines a cause of failure based on a mapping of the noisy data point to a distribution generated for the training dataset across multiple dimensions. The system determines a cause of failure based on an attribute of the noisy datapoint that deviates from the distribution of the training dataset and performs refinement towards the training dataset based on the identified cause of failure. The system retrains the machine learning model with the refined training dataset and sends the retrained machine learning model back to the client for re-deployment.

Abstract: A model management system adaptively refines a training dataset for more effective visual inspection. The system trains a machine learning model using the initial training dataset and sends the trained model to a client for deployment. The deployment process generates outputs that are sent back to the system. The system determines that performance of predictions for noisy data points are inadequate and determines a cause of failure based on a mapping of the noisy data point to a distribution generated for the training dataset across multiple dimensions. The system determines a cause of failure based on an attribute of the noisy datapoint that deviates from the distribution of the training dataset and performs refinement towards the training dataset based on the identified cause of failure. The system retrains the machine learning model with the refined training dataset and sends the retrained machine learning model back to the client for re-deployment.

Abstract: A processor receives an image of a syringe. After identifying a background and foreground of the image, where the foreground indicates pixels that may be associated with a defect, the processor subtracts the background to generate an updated image with an accentuated foreground. The processor applies a bounding box to a group of pixels in the foreground and inputs the bounding box into a classifier. The classifier outputs a label indicating whether the syringe is defective.

Abstract: This disclosure is directed to computing services that provide secure network connections using public-private key-based security for Internet of Things (IoT) devices, such as voice devices, that may have more than a predefined set of users. Device certificates that authorize IoT devices to access a secure network, such as an enterprise network and/or services eternal to an enterprise network are provided. A setup system may cooperate with an IoT device and a subordinate CA to generate a device certificate that allows the IoT device to access a secure enterprise network and services outside of the secure enterprise network. The IoT device may generate a certificate signing request (CSR) which may be signed by a remote subordinate CA to generate the device certificate using a root certificate of an enterprise CA. Systems are also disclosed that renew certificates for the IoT devices prior to their expiration.

Abstract: A processor receives an image of a syringe. After identifying a background and foreground of the image, where the foreground indicates pixels that may be associated with a defect, the processor subtracts the background to generate an updated image with an accentuated foreground. The processor applies a bounding box to a group of pixels in the foreground and inputs the bounding box into a classifier. The classifier outputs a label indicating whether the syringe is defective.

Abstract: Health care claims are managed and processed automatically. Data related to a plurality of health care claims is stored on a computer readable medium. The health care claims are retrieved from the computer readable medium, and each of the plurality of health care claims is assigned a type indicator with the processor from a set of type indicators that characterizes a health care service associated with each health care claim. The plurality of health care claims is then grouped based on the type indicator assigned to each of the health care claims. A programmed set of pricing rules is applied to the grouped plurality of health care claims to price each of the health care claims. The programmed set of pricing rules is derived from pricing standards for one or more health insurance systems.