Abstract: An example method includes (a) generating a request to obtain log data descriptive of operation of an autonomous vehicle control system in a subject scenario, the log data indexed by an indexing parameter; (b) submitting the request to a log repository service, the log repository service configured to receive the request and serve, responsive to the request, log metadata; (c) loading, based on the log metadata and an index value of the indexing parameter, a log data sketch associated with the index value; and (d) loading, based on the log metadata and the index value, and responsive to an inspection indicator, detailed log data associated with the index value.

Abstract: Embodiments for a metadata predictor. An index pipeline generates indices in an index buffer in which the indices are used for reading out a memory device. A prediction cache is populated with metadata of instructions read from the memory device. A prediction pipeline generates a prediction using the metadata of the instructions from the prediction cache, the populating of the prediction cache with the metadata of the instructions being performed asynchronously to the operating of the prediction pipeline.

Abstract: A hearing aid assembly includes a receiver speaker enclosed within a receiver housing. The receiver housing defines a circuitous receiver acoustic channel, wherein the receiver channel defines an open side along at least a portion of the receiver channel. The receiver channel also defines a pass-through passage extending from a first side of the receiver housing to a second side of the receiver housing, wherein the pass-through passage is partially defined by the wall defining a receiver opening. The hearing aid assembly also includes an earbud configured to fit over at least a portion of the receiver housing and partially cover the open side of the receiver channel.

Abstract: A method and system of training a spoken language understanding (SLU) model includes receiving natural language training data comprising (i) one or more speech recording, and (ii) a set of semantic entities and/or intents for each corresponding speech recording. For each speech recording, one or more entity labels and corresponding values, and one or more intent labels are extracted from the corresponding semantic entities and/or overall intent. A spoken language understanding (SLU) model is trained based upon the one or more entity labels and corresponding values, and one or more intent labels of the corresponding speech recordings without a need for a transcript of the corresponding speech recording.

Abstract: A detection and warning system for a refuse vehicle includes a camera and processing circuitry. The camera is configured to obtain image data of a target waste receptacle and a lift apparatus of the refuse vehicle. The processing circuitry is configured to predict, based on the image data, tipping of the target waste receptacle by the lift apparatus of the refuse vehicle. The processing circuitry is configured to, responsive to predicting tipping of the target waste receptacle, at least one of (i) operate an alert device to notify an operator of the predicted tipping, or (ii) limit operation of the lift apparatus.

Abstract: Systems and methods are provided for controlling operation of a vehicle. An example system for controlling operation of a vehicle includes one or more data collection components and one or more processors. The one or more data collection components are configured to collect data representative of a physical configuration of an interior vehicle component. The one or more processors are configured to access the collected data, determine, by processing the collected data, the physical configuration of the interior vehicle component, select a manner of operation based upon the determined physical configuration of the interior vehicle component, and cause the vehicle to operate according to the manner of operation.

Abstract: Aspects of the disclosure relate to detecting and identifying malicious sites using machine learning. A computing platform may receive a uniform resource locator (URL). The computing platform may parse and/or tokenize the URL to reduce the URL into a plurality of components. The computing platform may identify human-engineered features of the URL. The computing platform may compute a vector representation of the URL to identify deep learned features of the URL. The computing platform may concatenate the human-engineered features of the URL to the deep learned features of the URL, resulting in a concatenated vector representation. By inputting the concatenated vector representation of the URL to a URL classifier, the computing platform may compute a phish classification score. In response to determining that the phish classification score exceeds a first phish classification threshold, the computing platform may cause a cybersecurity server to perform a first action.

Abstract: Systems and methods for proximity device to device user interface management are disclosed. The systems and methods include a primary user device displaying variable data to a user assigned one or more tasks to be performed. In response to determining that the primary user device is within a predetermined range of an assistive device, the systems and methods pair the two devices, identify task data and/or other data, and modify a user interface displayed on the assistive device, where the modification occurs from device to device communication of displayed variable data and results in variable data from the primary user device being displayed on the assistive device.

Abstract: The present invention provides hepcidin analogues with improved in vivo half lives, and related pharmaceutical compositions and methods of use thereof.

Abstract: A system for optimizing charging for a vehicle having a rechargeable energy storage unit and travelling on a route includes a controller. The controller has a processor and tangible, non-transitory memory on which instructions are recorded. Execution of the instructions by the processor causes the controller to obtain details of the route, including surveying local charging infrastructure to determine availability of one or more charging stations within a predefined radius of the route. The controller is adapted to obtain respective station parameters pertaining to the one or more charging stations. Based on user input, at least one session goal is selected from a predefined set of goals. The controller is adapted to generate a recommended charging profile respectively for one or more stops along the route, based in part on the session goal and the respective station parameters.

Abstract: An additive manufacturing apparatus includes a stage configured to hold a component. A radiant energy device is operable to generate and project radiant energy in a patterned image. An actuator is configured to change a relative position of the stage relative to the radiant energy device. A resin management system includes a material deposition assembly upstream configured to deposit a resin on a resin support. The material deposition assembly includes a reservoir configured to retain a first volume of the resin and define a thickness of the resin on the resin support as the resin support is translated in an X-axis direction. The material deposition assembly further includes a vessel positioned above the reservoir in a Z-axis direction and configured to store a second volume of the resin. In addition, the material deposition assembly includes a conduit configured to direct the resin from the vessel to the reservoir.

Abstract: Displaying an indication of ancestral data is disclosed. An indication that a genetic interval corresponds to a reference interval that has a likelihood of having one or more ancestral origins is received. One or more graphic display parameters are determined based at least in part on the indication. An indication of the one or more ancestral origins is visually displayed using the one or more graphic display parameters.

Abstract: Systems and methods enable most valuable players (MVPs) of a gameplay session to play a bonus gameplay session where other players (non-MVP players) participate as player-spectators in online video games and, through a collective voting mechanism or through active interaction, determine the occurrence of certain events or contents of the bonus gameplay in real time. In this manner, non-MVP players are able to directly affect the course of the bonus gameplay.

Abstract: A fluid heating system including a burner unit is operated based on feedback control loops. The fluid heating system comprises a burner unit configured to heat a fluid, a sensor configured to sense a characteristic of the appliance, and a controller coupled to the burner unit and the sensor. The controller includes an electronic processor and a memory. The controller is configured to receive a first signal corresponding to the characteristic from the sensor, determine, based on the first signal, a first feedback loop control, control combustion of the burner unit based on the first feedback loop control, determine, based on the first feedback loop control, a second feedback loop control, and control combustion of the burner unit based on the second feedback loop control.

Abstract: A large-scale radio frequency signal collection and processing system comprising a plurality of sensor systems mounted on a plurality of collection platforms that integrates a plurality of overlapping datasets with differing characteristics (e.g., different resolutions, different view angles, different heights, different time periods, unrelated types of data) to generate an enriched dataset or datasets using a variety of processing techniques (e.g., statistical analysis, signal processing, image processing) that allows for more comprehensive analysis of the radio frequency signal landscape than would be possible using any of the datasets individually, or in combination but without such integration.

Abstract: Systems and methods for controlling a failover response of an autonomous vehicle are provided. In one example embodiment, a method includes determining, by one or more computing devices on-board an autonomous vehicle, an operational mode of the autonomous vehicle. The autonomous vehicle is configured to operate in at least a first operational mode in which a human driver is present in the autonomous vehicle and a second operational mode in which the human driver is not present in the autonomous vehicle. The method includes detecting a triggering event associated with the autonomous vehicle. The method includes determining actions to be performed by the autonomous vehicle in response to the triggering event based at least in part on the operational mode. The method includes providing one or more control signals to one or more of the systems on-board the autonomous vehicle to perform the one or more actions in response to the triggering event.

Abstract: Displaying a comparison of genetic data is disclosed, including receiving an indication of a first individual, receiving an indication of a second individual, retrieving the genotypic information for the first individual and the second individual, comparing the genotypic information of the first individual and the second individual, displaying an indication of the comparison of the genotypic information of the first individual and the second individual graphically. A first graphical symbol is used to display an indication of the genome regions for which the first individual and the second individual are identical. A second graphical symbol is used to display an indication of the genome regions for which the first individual and the second individual are half identical.

Abstract: Embodiments presented herein provide techniques for evaluating an asynchronous application using a test framework. The test framework may perform a load test of an asynchronous application or service composed from a collection of applications or services. To do so, the test framework may submit transactions to a distributed application at a specified transaction rate and monitor how the distributed application operates at that transaction rate. An aggregate load test component may evaluate the remaining work pending at work accumulation points of the distributed application to determine whether the distributed application can sustain the specified transaction rate. A transaction tracking component may initiate transactions to generate load at the specified transaction rate without blocking while the transactions are processed by the distributed application.

Abstract: Some embodiments provide a compiler for optimizing the implementation of a machine-trained network (e.g., a neural network) on an integrated circuit (IC). The compiler of some embodiments receives a specification of a machine-trained network including multiple layers of computation nodes and generates a graph representing options for implementing the machine-trained network in the IC. In some embodiments, the graph includes nodes representing options for implementing each layer of the machine-trained network and edges between nodes for different layers representing different implementations that are compatible. The graph is used, in some embodiments, to select an optimum set of cores for implementing the received machine-trained network. The compiler, in some embodiments, optimizes memory storage such that input and output layers of a single layer are not stored in a same memory unit.

Abstract: Apparatus and methods for extending functionality of memory controllers in a processor-based device are disclosed herein. In one aspect, a processor-based device provides a memory access intercept circuit that is communicatively coupled to a memory controller and a memory device. The memory access intercept circuit is configured to receive a memory write request that is directed to and received by the memory controller, and generates a write transaction identifier (ID) for the memory write request. The memory access intercept circuit then generates proxy write data containing the write transaction ID, and sends the proxy write data to the memory controller. The memory access intercept circuit subsequently intercepts the actual write data directed to the memory controller, and stores the write data in a write data buffer in association with the write transaction ID.