Abstract: Devices, systems, and methods are provided for surface-mounted leak detection on a printed circuit board. An example leak detection device includes a first and second electrical contact with a selectively conductive material disposed therebetween. At a first electrical conductivity of the selectively conductive material, the device has a first circuit state. The selectively conductive material is configured to change from the first electrical conductivity to a second electrical conductivity in an instance in which a predetermined amount of fluid is absorbed by the selectively conductive material. At the second electrical conductivity of the selectively conductive material, the device has a second circuit state indicative of a fluid leak. Corresponding systems and methods are also provided.

Abstract: Diagnostics and boot up for AV hardware and software of a computer system of an autonomous vehicle may be performed based at least on receiving a shutdown or power off indication, then a computing state of the computer system may be suspended with the computer system entering a low-power mode. The suspended computing state can be rapidly restored without requiring a reboot and diagnostics for key-on. To ensure the integrity of the saved computing state, the computer system may exit the low-power mode, rerun the diagnostics, reload the programs, and then reenter the low-power mode. Restoring the suspended computing state may be triggered by a user inserting an ignition key, pressing a button to turn on the vehicle, opening a door to the vehicle, remotely unlocking the vehicle, remotely starting the vehicle, etc.

Abstract: Apparatuses, systems, and techniques to enhance video are disclosed. In at least one embodiment, one or more neural networks are used to create a higher resolution video using upsampled frames from a lower resolution video.

Abstract: The disclosure provides a vehicle, a machine vision system, and a robot. In one example, the vehicle includes one or more processing units to implement a machine-learning model and to identify one or more objects depicted in one or more images using the machine-learning model, the machine-learning model being trained using a training dataset that includes a plurality of images procedurally synthesized according to one or more training image definitions.

Abstract: Various examples of the present disclosure include a stereoscopic deep neural network (DNN) that produces accurate and reliable results in real-time. Both LIDAR data (supervised training) and photometric error (unsupervised training) may be used to train the DNN in a semi-supervised manner. The stereoscopic DNN may use an exponential linear unit (ELU) activation function to increase processing speeds, as well as a machine learned argmax function that may include a plurality of convolutional layers having trainable parameters to account for context. The stereoscopic DNN may further include layers having an encoder/decoder architecture, where the encoder portion of the layers may include a combination of three-dimensional convolutional layers followed by two-dimensional convolutional layers.

Abstract: The disclosure relates to the transfer of visuals (e.g., window visuals) over virtual frames that may be stored in any number of video frames of one or more video streams. The visuals may be split into two-dimensional (2D) pages of a virtual frame, with each of the 2D pages being a fraction of the size of video frames of the video stream(s). The virtual frame may be encoded to the video frames of the video stream(s) and later reconstructed in accordance with a page table.

Abstract: Devices, systems, and techniques to incorporate lighting effects into computer-generated graphics. In at least one embodiment, a graphical frame depicting a virtual scene comprising is rendered by generating a record indicative of one or more lights in the virtual scene, and using the record to render a pixel. A second record, indicative of other lights in the virtual scene, is selected to combine with the first record, based at least in part on similarity between surfaces associated with the respective records. The combined record is used to render a pixel in a second graphical frame.

Abstract: In various examples, a timer component that generates an event when an interrupt request has not yet been cleared within at least a predetermined amount of time.

Abstract: In various examples, to support training a deep neural network (DNN) to predict a dense representation of a 3D surface structure of interest, a training dataset is generated using a parametric mathematical modeling. A variety of synthetic 3D road surfaces may be generated by modeling a 3D road surface using varied parameters to simulate changes in road direction and lateral surface slope. In an example embodiment, a synthetic 3D road surface may be created by modeling a longitudinal 3D curve and expanding the longitudinal 3D curve to a 3D surface, and the resulting synthetic 3D surface may be sampled to form a synthetic ground truth projection image (e.g., a 2D height map). To generate corresponding input training data, a known pattern that represents which pixels may remain unobserved during 3D structure estimation may be generated and applied to a ground truth projection image to simulate a corresponding sparse projection image.

Abstract: A multi-rank circuit system includes multiple transmitters each switchably coupled to a first end of a shared input/output (IO) channel and a unified receiver coupled to a second end of the shared IO channel. The unified receiver is coupled to apply an analog reference voltage to set a differential output of the unified receiver, and further configured to apply a variable digital code to adjust the differential output according to a particular one of the transmitters that is switched to the shared IO channel.

Abstract: In various examples, systems and methods are disclosed relating to registering image processing with image registration for image generation and content stream applications. Systems and methods are disclosed for registering portions of images that are modified to incorporate content or features, with references images from which the portions of the images are identified. The systems and methods can transform the modified portions to more realistically and precisely merge back into the reference images, such as for presentation as a content stream.

Abstract: Various embodiments include a computer memory system that dynamically adjusts a memory device performance feature, such as dynamic assist control, dynamic turbo mode, and/or the like, to improve the performance of memory devices in the memory system. The memory system enables or disables the memory device performance feature based on the operating voltage relative to a threshold voltage. If the operating voltage crosses the threshold voltage in one direction, then the memory device system enables the memory device performance feature. If the operating voltage crosses the threshold voltage in another direction, then the memory system disables the memory device performance feature. Various techniques enable the memory device performance feature to be employed even with complex integrated circuits that may include tens of thousands of devices that employ the memory device performance feature.

Abstract: In various examples, a trigger signal may be received that is indicative of a vehicle maneuver to be performed by a vehicle. A recommended vehicle trajectory for the vehicle maneuver may be determined in response to the trigger signal being received. To determine the recommended vehicle trajectory, sensor data may be received that represents a field of view of at least one sensor of the vehicle. A value of a control input and the sensor data may then be applied to a machine learning model(s) and the machine learning model(s) may compute output data that includes vehicle control data that represents the recommended vehicle trajectory for the vehicle through at least a portion of the vehicle maneuver. The vehicle control data may then be sent to a control component of the vehicle to cause the vehicle to be controlled according to the vehicle control data.

Abstract: Apparatuses, systems, and techniques to interpolate one or more intermediate images from two or more images is disclosed. In at least one embodiment, a processor includes one or more circuits to interpolate one or more intermediate images from two or more images based, at least in part, on one or more inconsistent flow vectors corresponding to the two or more images.

Abstract: Apparatuses, systems, and techniques to enhance video are disclosed. In at least one embodiment, one or more neural networks are used to create a higher resolution video using upsampled frames from a lower resolution video.

Abstract: Neural networks, in many cases, include convolution layers that are configured to perform many convolution operations that require multiplication and addition operations. Compared with performing multiplication on integer, fixed-point, or floating-point format values, performing multiplication on logarithmic format values is straightforward and energy efficient as the exponents are simply added. However, performing addition on logarithmic format values is more complex. Conventionally, addition is performed by converting the logarithmic format values to integers, computing the sum, and then converting the sum back into the logarithmic format. Instead, logarithmic format values may be added by decomposing the exponents into separate quotient and remainder components, sorting the quotient components based on the remainder components, summing the sorted quotient components using an asynchronous accumulator to produce partial sums, and multiplying the partial sums by the remainder components to produce a sum.

Abstract: A vehicle computing system validates location data received from a Global Navigation Satellite System receiver with other sensor data. In one embodiment, the system calculates velocities with the location data and the other sensor data. The system generates a probabilistic model for velocity with a velocity calculated with location data and variance associated with the location data. The system determines a confidence score by applying the probabilistic model to one or more of the velocities calculated with other sensor data. In another embodiment, the system implements a machine learning model that considers features extracted from the sensor data. The system generates a feature vector for the location data and determines a confidence score for the location data by applying the machine learning model to the feature vector. Based on the confidence score, the system can validate the location data. The validated location data is useful for navigation and map updates.

Abstract: A receiver receives communications over a communication channel, which may distort an incoming communication signal. In order to counter this distortion, the frequency response of the receiver is manipulated by adjusting several parameters. Each parameter controls at least a portion of the frequency response of the receiver. The optimal values for the parameters are determined by modifying an initial set of values for the parameters through one or more stochastic hill climbing operations until a performance metric associated with the receiver reaches a local optimum. The modified values are displaced through one or more mutation operations. The stochastic hill climbing operations may subsequently be performed on the mutated values to generate the final values for the parameters.

Abstract: In various examples, durations of relatively high user activity within a gameplay session may be determined from user input events using a running user activity measurement. Once a duration is identified, it may be further analyzed to merge the duration with one or more other durations and/or to determine or predict whether the duration would be of sufficient interest for further action. A user interest score for an identified duration may be computed based on a set of the user input events that occur in the duration and used to determine and/or predict whether the duration would be of sufficient interest for further action. In some cases, an action may be performed based on determining the user interest score is greater than a statistical value that is computed from user interest scores of multiple identified durations.

Abstract: Apparatuses, systems, and techniques to allocate one or more compute resources to a user device. In at least one embodiment, one or more circuits cause one or more compute resources to be allocated to two or more fifth-generation (5G) radio access network (RAN) cells based, at least in part, on interference between the two or more 5G RAN cells.