Abstract: Features extracted from one or more layers of a trained deep neural network (DNN) are used to detect out-of-distribution (OOD) data, such as anomalies. An OOD detection process includes inputting a feature output from a layer of the DNN into a trained autoencoder that applies an encoding function followed by a decoding function, resulting in a reconstructed feature. A feature reconstruction error is calculated based on a difference between the reconstructed feature and the original feature output from the DNN. The OOD detection process may further include calculating a score based on the feature reconstruction error and generating a visual representation of the feature reconstruction error.

Abstract: A method for identifying a tool anomaly of an printed circuit board (PCB) manufacturing process comprising a plurality of phases, the method comprising the steps of: obtaining image data of at least one tool of the PCB manufacturing process; inputting the image data to a machine learning module, the machine learning module configured to perform the following steps: extracting, from the image data, a tool feature image data of the at least one tool; classifying the image data into a phase of the plurality of phases; and determining, based on the classified image data and the tool feature image data, an anomaly state of the at least one tool.

Abstract: Features extracted from one or more layers of a trained deep neural network (DNN) are used to detect out-of-distribution (OOD) data, such as anomalies. An OOD detection process includes transforming a feature output from a layer of the DNN from a relatively high-dimensional feature space to a lower-dimensional space, and then performing a reverse transformation back to the higher-dimensional feature space, resulting in a reconstructed feature. A feature reconstruction error is calculated based on a difference between the reconstructed feature and the original feature output from the DNN. The OOD detection process may further include calculating a score based on the feature reconstruction error and generating a visual representation of the feature reconstruction error.

Abstract: Vehicle navigation control systems in autonomous driving rely on accurate predictions of objects within the vicinity of the vehicle to appropriately control the vehicle safely through its surrounding environment. Accordingly this disclosure provides methods and devices which implement mechanisms for obtaining contextual variables of the vehicle's environment for use in determining the accuracy of predictions of objects within the vehicle's environment.

Abstract: A safety system for a vehicle may include one or more processors configured to determine uncertainty data indicating uncertainty in one or more predictions from a driving model during operation of a vehicle; change or update one or more of the driving model parameters to one or more changed or updated driving model parameters based on the determined uncertainty data; and provide the one or more changed or updated driving model parameters to a control system of the vehicle for controlling the vehicle to operate in accordance with the driving model including the one or more changed or updated driving model parameters.

Abstract: Methods, apparatus, systems and articles of manufacture are disclosed to facilitate continuous learning. An example apparatus includes a trainer to train a first Bayesian neural network (BNN) and a second BNN, the first BNN associated with a first weight distribution and the second BNN associated with a second weight distribution. The example apparatus includes a weight determiner to determine a first sampling weight associated with the first BNN and a second sampling weight associated with the second BNN. The example apparatus includes a network sampler to sample at least one of the first weight distribution or the second weight distribution based on a pseudo-random number, the first sampling weight, and the second sampling weight. The example apparatus includes an inference controller to generate an ensemble weight distribution based on the sample.

Abstract: Methods, systems, and apparatus to obtain well-calibrated uncertainty in probabilistic deep neural networks are disclosed. An example apparatus includes a loss function determiner to determine a differentiable accuracy versus uncertainty loss function for a machine learning model, a training controller to train the machine learning model, the training including performing an uncertainty calibration of the machine learning model using the loss function, and a post-hoc calibrator to optimize the loss function using temperature scaling to improve the uncertainty calibration of the trained machine learning model under distributional shift.

Abstract: Techniques related to applying computer vision to decompressed video are discussed. Such techniques may include generating a region of interest in an individual video frame by translating spatial indicators of a first detected computer vision result from a reference video frame to the individual video frame and applying a greater threshold within the region of interest than outside of the region of interest for computer vision evaluation in the individual frame.

Abstract: Vehicle navigation control systems in autonomous driving rely on accurate predictions of objects within the vicinity of the vehicle to appropriately control the vehicle safely through its surrounding environment. Accordingly this disclosure provides methods and devices which implement mechanisms for obtaining contextual variables of the vehicle's environment for use in determining the accuracy of predictions of objects within the vehicle's environment.

Abstract: A safety system for a vehicle may include one or more processors configured to determine uncertainty data indicating uncertainty in one or more predictions from a driving model during operation of a vehicle; change or update one or more of the driving model parameters to one or more changed or updated driving model parameters based on the determined uncertainty data; and provide the one or more changed or updated driving model parameters to a control system of the vehicle for controlling the vehicle to operate in accordance with the driving model including the one or more changed or updated driving model parameters.

Abstract: Techniques related to applying computer vision to decompressed video are discussed. Such techniques may include generating a region of interest in an individual video frame by translating spatial indicators of a first detected computer vision result from a reference video frame to the individual video frame and applying a greater threshold within the region of interest than outside of the region of interest for computer vision evaluation in the individual frame.

Abstract: Techniques related to applying computer vision to decompressed video are discussed. Such techniques may include generating a region of interest in an individual video frame by translating spatial indicators of a first detected computer vision result from a reference video frame to the individual video frame and applying a greater threshold within the region of interest than outside of the region of interest for computer vision evaluation in the individual frame.

Abstract: Techniques related to applying computer vision to decompressed video are discussed. Such techniques may include generating a region of interest in an individual video frame by translating spatial indicators of a first detected computer vision result from a reference video frame to the individual video frame and applying a greater threshold within the region of interest than outside of the region of interest for computer vision evaluation in the individual frame.

Abstract: Methods and apparatuses use a pixel-adaptive interpolation algorithm to provide image upscaling. For each pixel location, the algorithm determines whether to use a high quality scaler algorithm (such as a polyphase filter, for example) or a directional interpolator to determine the pixel value. The determination of the appropriate interpolation algorithm is based on whether the pixel is determined to be an edge. If the pixel is determined to be an edge, the pixel-adaptive interpolation algorithm may use the directional interpolator to process the pixel; otherwise, the pixel is processed using a scaler algorithm.

Abstract: Methods and apparatuses use a pixel-adaptive interpolation algorithm to provide image upscaling. For each pixel location, the algorithm determines whether to use a high quality scaler algorithm (such as a polyphase filter, for example) or a directional interpolator to determine the pixel value. The determination of the appropriate interpolation algorithm is based on whether the pixel is determined to be an edge. If the pixel is determined to be an edge, the pixel-adaptive interpolation algorithm may use the directional interpolator to process the pixel; otherwise, the pixel is processed using a scaler algorithm.