Abstract: In various examples, determining emotion sequences for speech in conversational AI systems and applications is described herein. Systems and methods are disclosed that use one or more first machine learning models to determine a sequence of emotional states associated with audio data representing speech. To use the first machine learning model(s), the systems and methods may train the first machine learning model(s) using one or more second machine learning models, where the second machine learning model(s) is trained to determine scores indicating accuracies associated with sequences of emotional states. For instance, the second machine learning model(s) may be trained to determine the scores using audio data representing speech, sequences of emotional states associated with the speech, and indications of which sequences of emotional states better represent the speech as compared to other sequences of emotional states.

Abstract: In various examples, systems and methods are disclosed that relate to data augmentation for training/updating perception models in autonomous or semi-autonomous systems and applications. For example, a system may receive data associated with a set of frames that are captured using a plurality of cameras positioned in fixed relation relative to the machine; generate a panoramic view based at least on the set of frames; provide data associated with the panoramic view to a model to cause the model to generate a high dynamic range (HDR) panoramic view; determine lighting information associated with a light distribution map based at least on the HDR panoramic view; determine a virtual scene; and render an asset and a shadow on at least one of the frames, based at least on the virtual scene and the light distribution map, the shadow being a shadow corresponding to the asset.

Abstract: In various examples, a deep neural network (DNN) may be used to detect and classify animate objects and/or parts of an environment. The DNN may be trained using camera-to-LiDAR cross injection to generate reliable ground truth data for LiDAR range images. For example, annotations generated in the image domain may be propagated to the LiDAR domain to increase the accuracy of the ground truth data in the LiDAR domain—e.g., without requiring manual annotation in the LiDAR domain. Once trained, the DNN may output instance segmentation masks, class segmentation masks, and/or bounding shape proposals corresponding to two-dimensional (2D) LiDAR range images, and the outputs may be fused together to project the outputs into three-dimensional (3D) LiDAR point clouds. This 2D and/or 3D information output by the DNN may be provided to an autonomous vehicle drive stack to enable safe planning and control of the autonomous vehicle.

Abstract: In various examples, systems and methods are disclosed relating to decider networks for reactive decision-making, including for control of robotic systems. The decider networks can allow robotic systems to operate more collaboratively, such as by allowing the robotic systems to more frequently process and react to dynamic states of the environment and objects in the environment, such as to change decisions and/or paths of decision execution responsive to dynamic changes in logical states. The decider network can include a plurality of nodes having functions to process the logical states in sequence to determine actions for the robotic systems to perform.

Abstract: In various examples, techniques for multi-dimensional tracking of objects using two-dimensional (2D) sensor data are described. Systems and methods may use first image data to determine a first 2D detected location and a first three-dimensional (3D) detected location of an object. The systems and methods may then determine a 2D estimated location using the first 2D detected location and a 3D estimated location using the first 3D detected location. The systems and methods may use second image data to determine a second 2D detected location and a second 3D detected location of a detected object, and may then determine that the object corresponds to the detected object using the 2D estimated location, the 3D estimated location, the second 2D detected location, and the second 3D detected location. The systems and method then generate, modify, delete, or otherwise update an object track that includes 2D state information and 3D state information.

Abstract: In various examples, probabilistic-based techniques may be used to predict intended paths of machines through an environment. For instance, various input data from perception systems, localization systems, mapping systems, and/or other sources of data may be used to determine occupant intent and compute scores associated with road segments in an environment. The scores may indicate a probability that certain road segments are part of the occupant's intended path for the machine, and the scores may be aggregated for each of the road segments across multiple instances of receiving an analyzing the input data. In some instances, a highest scoring road segment(s) may be selected as part of a predicted path of the machine. For instance, at a junction(s) where multiple road segments meet, the highest scoring road segment(s) may be selected as the predicted path.

Abstract: A device includes a printed circuit board (PCB) including a signal trace electrically coupled to a signal via. The device further includes a slot ground configured to reduce signal interference with respect to the signal via. The slot ground includes a slot formed in the PCB at least partially surrounding the signal via. The slot ground further includes metal plating on a wall of the slot. The metal plating is electrically coupled to a ground plane of the PCB. The slot ground further includes resin at least partially filling the slot.

Abstract: A device includes a printed circuit board (PCB) including a signal trace electrically coupled to a signal via. The device further includes a coaxial ground shield configured to reduce signal interference with respect to the signal via. The coaxial ground shield includes a ground via formed in the PCB substantially surrounding the signal via and substantially coaxial with the signal via. The coaxial ground shield further includes metal plating on a wall of the ground via. The metal plating is electrically coupled to a ground plane of the PCB. The coaxial ground shield further includes resin at least partially filling the ground via.

Abstract: A first virtual address is translated into a first physical address using a first translation agent associated with a first I/O device of a system. The first physical address is associated with an address space of the first I/O device. A first address translation request is sent to a second translation agent associated with a CPU of the system. The first address translation request includes the first physical address. A first address translation response is received from the second translation agent. The first address translation response includes a second physical address. The second physical address is associated with an address space of the system.

Abstract: In various examples, query-based evaluation of error patterns in annotated training data for machine learning systems and applications is provided. An error pattern evaluator may include an error pattern extraction function and an error pattern search algorithm. An annotated validation sample associated with an inaccurate prediction from a machine learning model may be analyzed to extract an error pattern. A set of annotated training data used for training the machine learning model may be analyzed by the error pattern extraction function to generate an error pattern for individual samples of annotated training data to define a search dataset. An error pattern search algorithm may use the error pattern derived from the inaccurate prediction as a query to search the dataset to identify each occurrence of samples having an error pattern similar to the query error pattern. The set of annotated training data may be corrected based on the search results.

Abstract: In various examples, systems and methods are disclosed that provide highly accurate gaze predictions that are specific to a particular user by generating and applying, in deployment, personalized calibration functions to outputs and/or layers of a machine learning model. The calibration functions corresponding to a specific user may operate on outputs (e.g., gaze predictions from a machine learning model) to provide updated values and gaze predictions. The calibration functions may also be applied one or more last layers of the machine learning model to operate on features identified by the model and provide values that are more accurate. The calibration functions may be generated using explicit calibration methods by instructing users to gaze at a number of identified ground truth locations within the interior of the vehicle. Once generated, the calibration functions may be modified or refined through implicit gaze calibration points and/or regions based on gaze saliency maps.

Abstract: Disclosed are systems and techniques that may generate task-oriented assistant responses to natural language requests of a user. The techniques include receiving a natural language request of a user and generating a task-oriented assistant response based on the natural language request. Generating the task-oriented assistant response includes converting the natural language request into a first set of tokens using a first machine learning model, applying a large language model (LLM) to the first set of tokens to obtain dialogue state information, modifying the dialogue state information using system state information, and determining a natural language response using the LLM and the modified dialogue state information, where the natural language response is the task-oriented response.

Abstract: The disclosure provides an improved pre-decoding scheme that uses pre-decoders with multiple decoders that generate clocked pre-decoded signals, which reduces address set-up time and hold. The ordering of the address bits processed by the multiple decoders is also arranged to advantageously allow sharing logic gates of the multiple decoders, sharing of nodes of the logic gates, or sharing a combination of both. In one example, a memory circuit is disclosed that includes: (1) an array of memory cells arranged in rows and columns, and (2) an address decoder for decoding a binary address to assert wordlines associated with the rows, wherein the address decoder has (2A) a row decoder for asserting one of the wordlines based on clocked-pre-decode signals, and (2B) a pre-decoder having multiple decoders that generate the clocked pre-decode signals from the binary address and provide the clocked pre-decode signals to the row decoder for the asserting.

Abstract: Neural network performance is improved in terms of training speed, memory footprint, and/or accuracy by learning a compressed neural graphics primitive representation. A neural graphics primitive is a mathematical function involving at least one neural network, used to represent a computer graphic, where the graphic can be an image, a 3D shape, a light field, a signed distance function, a radiance field, 2D video, volumetric video, etc. Instead of being input directly to a neural network, inputs are effectively mapped (encoded) into a higher dimensional space via a function. The input comprises coordinates used to identify a point within a d-dimensional space. The point is quantized and a set of vertex coordinates corresponding to the point are used to access an indexing codebook and a features codebook that store learned index offsets and learned feature vectors, respectively. The learned feature vectors are then provided as inputs to the neural network.

Abstract: In various examples, determining emotional states for speech in conversational artificial intelligence (AI) and/or digital avatar systems and applications is descried herein. Systems and methods are disclosed that use one or more machine learning models to determine one or more emotional states associated with speech, where the machine learning model(s) may be trained using various processes. For instance, in some examples, the machine learning model(s) may be trained during a first training process to determine probabilities for distributions of values, where the distributions model different emotional states. For example, a distribution may include a first value for angry, a second value for happy, a third value for sad, and/or so forth. Additionally, or alternatively, in some examples, the machine learning model(s) may be trained during a second training process to more precisely determine the actual emotional states (and/or the probabilities) based on training data representing human feedback.

Abstract: Apparatuses, systems, and techniques to perform an application programming interface (API) to add one or more graph nodes to a software graph, wherein the API is to cause a semaphore update node to be added to a software graph based, at least in part, on a dependency type indicated by the API. In at least one embodiment, one or more nodes are added to a graph in accordance to one or more dependency types.

Abstract: In various examples, based on spatial index values corresponding to first assignments of a first set of bins to spatial elements of a space, second assignments may be determined of a second set of bins to at least two spatial elements. The second assignments may at least partially overwrite corresponding assignments of the first assignments and may be used to determine partitions of the at least two spatial elements. The second assignments may be determined based on the first assignments indicating multiple spatial elements correspond to a same subregion of the space. The first assignments may be used to determine a first portion of a partitioning of the spatial elements. The second assignments may be used to partition a subset of the spatial elements to determine a second portion of the partitioning of the spatial elements, which may further partition one or more nodes from the first portion.

Abstract: In various examples, spatial elements of a scene may be projected into multi-dimensional bins that correspond to a spatial partitioning of the scene to determine assignments between the spatial elements and the multi-dimensional bins. A partition of the spatial elements may be determined using the assignments and a spatial element may be assigned to a node corresponding to a hierarchical partitioning of the spatial elements based on the partition. To determine the partition, candidate split planes may be determined with respect to the multi-dimensional bins, and a split plane that defines the partition may be selected from the candidate split planes. The assignments and the multi-dimensional bins may also be used to determine subpartitions of the partition. For example, the assignments may be used to determine the subpartitions with respect to a subset of the multi-dimensional bins that corresponds to the partition.

Abstract: Systems and methods for cooling a datacenter are disclosed. In at least one embodiment, a primary cooling loop includes at least one primary flow controller to control flow of a primary coolant to a coolant distribution unit (CDU) at a primary flow rate that is determined based in part on heat generated from one or more computing devices that is to be addressed by a secondary coolant, which is to be cooled in a CDU by a primary coolant at a primary flow rate enabled by at least one primary flow controller.

Abstract: In various examples, systems and methods of the present disclosure combine open and closed dialog systems into an intelligent dialog management system. A text query may be processed by a natural language understanding model trained to associate the text query with a domain tag, intent classification, and/or input slots. Using the domain tag, the natural language understanding model may identify information in the text query corresponding to input slots needed for answering the text query. The text query and related information may then be passed to a dialog manager to direct the text query to the proper domain dialog system. Responses retrieved from the domain dialog system may be provided to the user via text output and/or via a text to speech component of the dialog management system.