Abstract: In various examples, surface profile estimation and bump detection may be performed based on a three-dimensional (3D) point cloud. The 3D point cloud may be filtered in view of a portion of an environment including drivable free-space, and within a threshold height to factor out other objects or obstacles other than a driving surface and protuberances thereon. The 3D point cloud may be analyzed—e.g., using a sliding window of bounding shapes along a longitudinal or other heading direction—to determine one-dimensional (1D) signal profiles corresponding to heights along the driving surface. The profile itself may be used by a vehicle—e.g., an autonomous or semi-autonomous vehicle—to help in navigating the environment, and/or the profile may be used to detect bumps, humps, and/or other protuberances along the driving surface, in addition to a location, orientation, and geometry thereof.

Abstract: Systems and methods for operating a datacenter are disclosed. In at least one embodiment, hybrid cooling unit is disclosed wherein an evaporative cooler is to provide a source of cooled air and a liquid heat exchanger is to provide a source of cooled liquid for cooling one or more electronic components, the hybrid cooling unit further including an air inlet to direct a flow of external air to remove heat from the evaporative cooler and the liquid heat exchanger.

Abstract: Methods and structures are described for detecting clock anomalies. Example methods include measuring a duration of a first phase of the clock signal, monitoring a duration of a second phase of the clock signal, and determining whether the duration of the second phase has exceeded the measured duration of the first phase. If so, a clock stop detection signal is asserted. Example structures include a detector circuit having an input for sensing the clock signal. The circuit is operable to measure a duration of a first clock phase instance, to monitor a duration of a second clock phase instance, and to assert an output if the duration of the second clock phase instance exceeds the measured duration of the first clock phase instance.

Abstract: Systems and methods for determining the gaze direction of a subject and projecting this gaze direction onto specific regions of an arbitrary three-dimensional geometry. In an exemplary embodiment, gaze direction may be determined by a regression-based machine learning model. The determined gaze direction is then projected onto a three-dimensional map or set of surfaces that may represent any desired object or system. Maps may represent any three-dimensional layout or geometry, whether actual or virtual. Gaze vectors can thus be used to determine the object of gaze within any environment. Systems can also readily and efficiently adapt for use in different environments by retrieving a different set of surfaces or regions for each environment.

Abstract: The present invention provides methods, systems, computer program products that use deep learning with neural networks to denoise ATAC-seq datasets. The methods, systems, and programs provide for increased efficiency, accuracy, and speed in identifying genomic sites of chromatin accessibility in a wide range of tissue and cell types.

Abstract: Systems and methods for automatic camera calibration without using a robotic actuator or similar hardware. An electronic display screen projects an image of a simulated three-dimensional calibration pattern, such as a checkerboard, oriented in a particular pose. The camera captures an image of the calibration pattern that is displayed on the screen, and this image together with the transform of the simulated three-dimensional calibration pattern are used to calibrate the camera. Multiple different pictures of different poses are employed to determine the optimal set of poses that produces the lowest reprojection error. To aid in selecting different poses, i.e., spatial positions and orientations of the simulated three-dimensional calibration pattern, poses may be selected from only that portion of the camera's field of view which is expected to be typically used in operation of the camera.

Abstract: The disclosure provides computer systems for processing paths and a renderer that generates a stroked tessellation of a path. A data structure for processing the paths can be used, wherein the data structure is an array of indexed links that compactly encode a path. The position of one or more index values, such as a null index value, within an indexed link can encode a link's type. In one example, the computer system for processing links of a path includes one or more processing units to perform one or more operations including: (1) analyzing a data structure that encodes a link of a path, the data structure having multiple indices that refer to a control point coordinate array corresponding to the link, and (2) determining a type of the link based on a presence of at least one index null value for at least one of the indices.

Abstract: A graph neural network to predict net parasitics and device parameters by transforming circuit schematics into heterogeneous graphs and performing predictions on the graphs. The system may achieve an improved prediction rate and reduce simulation errors.

Abstract: Automated detection of events in content can be performed using regions of information associated with various user interface or display elements. Certain elements can be indicative of a type of event, and regions associated with these elements can be analyzed on a per-frame basis. If one of these primary regions shows a state or transition that is indicative of one of these events, one or more secondary regions can be analyzed as well to attempt to verify whether that event occurred, as well as whether that event qualifies for selection for additional use. Selected events can be used for purposes such as to generate highlight montages, training videos, or user profiles. These events may be positioned at different layers of an event hierarchy, where child regions are only analyzed for frames where a parent region is indicative of a type of event.

Abstract: In various examples, one or more deep neural networks (DNNs) are executed to regress on control points of a curve, and the control points may be used to perform a curve fitting operation—e.g., Bezier curve fitting—to identify landmark locations and geometries in an environment. The outputs of the DNN(s) may thus indicate the two-dimensional (2D) image-space and/or three-dimensional (3D) world-space control point locations, and post-processing techniques—such as clustering and temporal smoothing—may be executed to determine landmark locations and poses with precision and in real-time. As a result, reconstructed curves corresponding to the landmarks—e.g., lane line, road boundary line, crosswalk, pole, text, etc.—may be used by a vehicle to perform one or more operations for navigating an environment.

Abstract: In one embodiment, a system receives pixel data from a pair of regions of an image generated by an imaging device, the pair of regions includes a first region and a second region, where the first region includes a first plurality of pixels and the second region includes a second plurality of pixels. The system determines a plurality of pixel pairs, where a pixel pair includes a first pixel from the first plurality of pixels and a second pixel from the second plurality of pixels. The system calculates a plurality of contrasts based on the plurality of pixel pairs. The system determines a contrast distribution based on the plurality of contrasts. The system calculates a value representative of a capability of the imaging device to detect contrast based on the contrast distribution. The system determines a reduction in contrast detectability of the imaging device based on the value.

Abstract: A method for forming a printed circuit board includes: forming on a substrate a first conductive layer for a first edge connector pin and a first conductive layer for a second edge connector pin, wherein the first conductive layer for the first edge connector pin and the first conductive layer for the second edge connector pin are electrically coupled to one another via a first conductive layer for an electrical bridging element; electroplating a second conductive layer onto both the first conductive layer for the first edge connector pin and the first conductive layer for the second edge connector pin via a plating current conductor; and removing at least a portion of the electrical bridging element to electrically separate the first edge connector pin from the second edge connector pin.

Abstract: In various examples, live perception from sensors of a vehicle may be leveraged to detect and classify intersections in an environment of a vehicle in real-time or near real-time. For example, a deep neural network (DNN) may be trained to compute various outputs—such as bounding box coordinates for intersections, intersection coverage maps corresponding to the bounding boxes, intersection attributes, distances to intersections, and/or distance coverage maps associated with the intersections. The outputs may be decoded and/or post-processed to determine final locations of, distances to, and/or attributes of the detected intersections.

Abstract: Various approaches are disclosed to virtualizing intrusion detection and prevention. Disclosed approaches provide for an embedded system having a hypervisor that provides a virtualized environment supporting any number of guest OSes. The virtualized environment may include a security engine on an internal communication channel between the guest OS and a virtualized hardware interface (e.g., an Ethernet or CAN interface) to analyze network traffic to protect the guest OS from other guest OSes or other network components, and to protect those network components from the guest OS. The security engine may be on a different partition than the guest OS and the virtualized hardware interface providing the components with isolated execution environments that protect against malicious code execution. Each guest OS may have its own security engine customized for the guest OS to account for what is typical or expected traffic for the guest OS.

Abstract: Robust temporal gradients, representing differences in shading results, can be computed between current and previous frames in a temporal denoiser for ray-traced renderers. Backward projection can be used to locate matching surfaces, with the relevant parameters of those surfaces being carried forward and used for patching. Backward projection can be performed for each stratum in a current frame, a stratum representing a set of adjacent pixels. A pixel from each stratum is selected that has a matching surface in the previous frame, using motion vectors generated during the rendering process. A comparison of the depth of the normals, or the visibility buffer data, can be used to determine whether a given surface is the same in the current frame and the previous frame, and if so then parameters of the surface from the previous frame G-buffer is used to patch the G-buffer for the current frame.

Abstract: Disclosed approaches may provide for non-blocking video processing pipelines that have the ability to efficiently share transform hardware resources. Transform hardware resources may be shared across processing parameters, such as pixel block dimensions, transform types, video stream bit depths, and/or multiple coding formats, as well as for inter-frame and intra-frame encoding. The video processing pipeline may be divided into phases, each phase having half-butterfly circuits to perform a respective portion of computations of a transform. The phases may be selectable and configurable to perform transforms for multiple different combinations of the processing parameters. In each configuration, the phases may be capable of performing a transform by a sequential pass through at least some of the phases resulting in high throughput. Approaches are also described related to improving the performance and efficiency of transpose operations of transforms.

Abstract: Autonomous driving is one of the world's most challenging computational problems. Very large amounts of data from cameras, RADARs, LIDARs, and HD-Maps must be processed to generate commands to control the car safely and comfortably in real-time. This challenging task requires a dedicated supercomputer that is energy-efficient and low-power, complex high-performance software, and breakthroughs in deep learning AI algorithms. To meet this task, the present technology provides advanced systems and methods that facilitate autonomous driving functionality, including a platform for autonomous driving Levels 3, 4, and/or 5. In preferred embodiments, the technology provides an end-to-end platform with a flexible architecture, including an architecture for autonomous vehicles that leverages computer vision and known ADAS techniques, providing diversity and redundancy, and meeting functional safety standards.

Abstract: A method, computer readable medium, and system are disclosed for visual sequence learning using neural networks. The method includes the steps of replacing a non-recurrent layer within a trained convolutional neural network model with a recurrent layer to produce a visual sequence learning neural network model and transforming feedforward weights for the non-recurrent layer into input-to-hidden weights of the recurrent layer to produce a transformed recurrent layer. The method also includes the steps of setting hidden-to-hidden weights of the recurrent layer to initial values and processing video image data by the visual sequence learning neural network model to generate classification or regression output data.

Abstract: A hardware-based traversal coprocessor provides acceleration of tree traversal operations searching for intersections between primitives represented in a tree data structure and a ray. The primitives may include opaque and alpha triangles used in generating a virtual scene. The hardware-based traversal coprocessor is configured to determine primitives intersected by the ray, and return intersection information to a streaming multiprocessor for further processing. The hardware-based traversal coprocessor is configured to omit reporting of one or more primitives the ray is determined to intersect. The omitted primitives include primitives which are provably capable of being omitted without a functional impact on visualizing the virtual scene.

Abstract: A receiving link device includes a receiver (RX) to receive a data signal from a transmitting link device, the receiver including an equalizer to detect RX tap values and a processing device coupled to the receiver, the processing device to perform operations including: programming the receiver with information related to target RX tap values that are associated RX pre-cursors or RX post-cursors; detecting, using the equalizer, that an RX pre-cursor value is greater or less than a target RX tap value; generating, based on the detecting, a tap message including an up or a down command to decrease or increase a corresponding transmitter (TX) pre-cursor value of the transmitting link device; and causing the tap message to be provided to a local transmitter to be transmitted to a remote receiver of the transmitting link device, which causes the transmitting link device to adjust the corresponding TX pre-cursor value.