Abstract: Wireless circuitry can include a processor that generates a baseband signal, an upconversion circuit that upconverts the baseband signals to a radio-frequency signal, and an amplifier that amplifies the radio-frequency signal. A tunable delay circuit can be used to selectively delay generation of the radio-frequency signal or to delay generation of another signal intended for the radio-frequency amplifier. The tunable delay circuit can be controlled using a closed-loop delay adaptation scheme. A feedback receiver that is coupled to an output of the amplifier can be used to generate a demodulated signal. A delay error measurement circuit can be used to receive the demodulated signal, to detect a peak by monitoring when an envelope of the demodulated signal crosses a threshold level, to compute an amount of asymmetry in the detected peak, and to output a signal that is used to control the tunable delay circuit.

Abstract: In various examples, a cell model that partitions a geographic region into one or more cells is used to determine clusters of cell which share similarities. Sensor data is provided to one or more machine learning models trained to classify the sensor data to one or more cells of the cell model. Based on classifying sensor data to cells of a cell model, similarities between pairings of cells of the cell model may be determined and used to form clusters of the cell which are sufficiently similar in order to aid in the curation of training data used to train machine learning models in order to aid an autonomous or semi-autonomous machine in a surrounding environment.

Abstract: In various examples, map data or geospatial data is used to identify a subset of sensor data having a higher likelihood of including representations of a target object of interest from a larger set of sensor data. Feature vectors corresponding to the subset of sensor data may then be compared to template feature vectors corresponding to the target object in order to confirm the depiction of the target object in the sensor data. The identified sensor data may be used to train one or more machine learning model to compute outputs that correspond to object identification. The trained machine learning models may be used to identify objects in order to aid an autonomous or semi-autonomous machine in a surrounding environment.

Abstract: Apparatuses, systems, and techniques to automatically select training data. In at least one embodiment, training data is automatically selected based on, for example, metadata associated with the training data.

Abstract: Approaches presented herein provide for semantic data matching, as may be useful for selecting data from a large unlabeled dataset to train a neural network. For an object detection use case, such a process can identify images within an unlabeled set even when an object of interest represents a relatively small portion of an image or there are many other objects in the image. A query image can be processed to extract image features or feature maps from only one or more regions of interest in that image, as may correspond to objects of interest. These features are compared with images in an unlabeled dataset, with similarity scores being calculated between the features of the region(s) of interest and individual images in the unlabeled set. One or more highest scored images can be selected as training images showing objects that are semantically similar to the object in the query image.

Abstract: A communication system using adaptive sample rate reduction (ASRR) is disclosed. The system includes a digital front end (DFE) and a radio frequency (RF) interface. The DFE is configured to receive a baseband signal, identify reduced performance parameters for the baseband signal, reduce a sampling rate for the baseband signal based on the reduced performance parameters and generate a digital interface signal using the reduced sampling rate. The RF interface is configured to generate an analog TX signal from the digital interface signal.

Abstract: A method for distributing sets of regular expressions to a fixed number of state machine engines includes combining, with a processing device, a plurality of regular expressions into a single compound regular expression, creating a single nondeterministic finite automaton (NFA) including a plurality of NFA states based on the compound regular expression, performing an interference analysis for each pair of NFA states to identify all pairs of NFA states that would potentially interfere in an equivalent deterministic finite automaton (DFA), creating an interference graph representing the regular expressions associated with potentially interfering NFA states based on the results of the interference analysis, and performing a graph coloring algorithm on the interference graph to assign a different color to each represented regular expression in the graph.

Abstract: A method for distributing sets of regular expressions to a fixed number of state machine engines includes combining, with a processing device, a plurality of regular expressions into a single compound regular expression, creating a single nondeterministic finite automaton (NFA) including a plurality of NFA states based on the compound regular expression, performing an interference analysis for each pair of NFA states to identify all pairs of NFA states that would potentially interfere in an equivalent deterministic finite automaton (DFA), creating an interference graph representing the regular expressions associated with potentially interfering NFA states based on the results of the interference analysis, and performing a graph coloring algorithm on the interference graph to assign a different color to each represented regular expression in the graph.

Abstract: The invention comprises a system and method for employing video in development processes. A new theory of operation for mapping video to formal models is disclosed. The present invention combines a runtime component and an object memory with an transformer component and offers several inputs and outputs. At least one capture device allows input of video. Video is structurally decomposed into shots and annotated following a semiology-based video model and stored in object memory. A runtime component determines the shots that are played back on one or more displays. A spectator may influence the runtime component by changing its state via at least one controller. One or more downstream development processes can access the object memory to extract customary models for requirements specification.

Abstract: The invention comprises a system and method for employing video in development processes. A new theory of operation for mapping video to formal models is disclosed. The present invention combines a runtime component and an object memory with an transformer component and offers several inputs and outputs. At least one capture device allows input of video. Video is structurally decomposed into shots and annotated following a semiology-based video model and stored in object memory. A runtime component determines the shots that are played back on one or more displays. A spectator may influence the runtime component by changing its state via at least one controller. One or more downstream development processes can access the object memory to extract customary models for requirements specification.

Abstract: The invention comprises a system and method for employing video in development processes. A new theory of operation for mapping video to formal models is disclosed. The present invention combines a runtime component and an object memory with an transformer component and offers several inputs and outputs. At least one capture device allows input of video. Video is structurally decomposed into shots and annotated following a semiology-based video model and stored in object memory. A runtime component determines the shots that are played back on one or more displays. A spectator may influence the runtime component by changing its state via at least one controller. One or more downstream development processes can access the object memory to extract customary models for requirements specification. The present invention can play a useful role for development teams that are distributed over large areas by providing common reference points in shots representing the application domain.