In various examples, a deep neural network (DNN) is trained to accurately predict, in deployment, distances to objects and obstacles using image data alone. The DNN may be trained with ground truth data that is generated and encoded using sensor data from any number of depth predicting sensors, such as, without limitation, RADAR sensors, LIDAR sensors, and/or SONAR sensors. Camera adaptation algorithms may be used in various embodiments to adapt the DNN for use with image data generated by cameras with varying parameters—such as varying fields of view. In some examples, a post-processing safety bounds operation may be executed on the predictions of the DNN to ensure that the predictions fall within a safety-permissible range.
B60W 60/00 - Drive control systems specially adapted for autonomous road vehicles
G06F 18/214 - Generating training patterns; Bootstrap methods, e.g. bagging or boosting
G06V 10/762 - Arrangements for image or video recognition or understanding using pattern recognition or machine learning using clustering, e.g. of similar faces in social networks
G06V 20/56 - Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
2.
HYBRID LANGUAGE MODELS FOR CONVERSATIONAL AI SYSTEMS AND APPLICATIONS
In various examples, first textual data may be applied to a first MLM to generate an intermediate speech representation (e.g., a frequency-domain representation), the intermediate audio representation and a second MLM may be used to generate output data indicating second textual data, and parameters of the second MLM may be updated using the output data and ground truth data associated with the first textual data. The first MLM may include a trained Text-To-Speech (TTS) model and the second MLM may include an Automatic Speech Recognition (ASR) model. A generator from a generative adversarial networks may be used to enhance an initial intermediate audio representation generated using the first MLM and the enhanced intermediate audio representation may be provided to the second MLM. The generator may include generator blocks that receive the initial intermediate audio representation to sequentially generate the enhanced intermediate audio representation.
Systems and techniques for performing multicast-reduction operations. In at least one embodiment, a network device receives first network data associated with a multicast operation to be collectively performed by at least a plurality of endpoints. The network device reserves resources to process second network data to be received from the endpoints, and sends the first network data to a plurality of additional network devices. The network device receives the second network data, and processes the second network data using the reserved resources.
A method and system for performing novel image synthesis using generative networks are provided. The encoder-based model is trained to infer a 3D representation of an input image. A feature image is then generated using volume rendering techniques in accordance with the 3D representation. The feature image is then concatenated with a noisy image and processed by a denoiser network to predict an output image from a novel viewpoint that is consistent with the input image. The denoiser network can be a modified Noise Conditional Score Network (NCSN). In some embodiments, multiple input images or keyframes can be provided as input, and a different 3D representation is generated for each input image. The feature image is then generated, during volume rendering, by sampling each of the 3D representations and applying a mean-pooling operation to generate an aggregate feature image.
G06T 5/50 - Image enhancement or restoration by the use of more than one image, e.g. averaging, subtraction
G06V 10/44 - Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
G06V 10/771 - Feature selection, e.g. selecting representative features from a multi-dimensional feature space
5.
ASYNCHRONOUS IN-SYSTEM TESTING FOR AUTONOMOUS SYSTEMS AND APPLICATIONS
Systems and methods are disclosed that relate to testing processing elements of an integrated processing system. A first system test may be performed on a first processing element of an integrated processing system. The first system test may be based at least on accessing a test node associated with the first processing element. The first system test may be accessed using a first local test controller. A second system test may be performed on a second processing element of the integrated processing system. The second system test may be based at least on accessing a second test node associated with the second processing element. The second system test may be accessed using a second local test controller.
In various examples, a stitched image may be generated from overlapping image frames using a dynamic seam placement that depends on scene content and/or other factors. Since an optimized seam placement may jump from a previous location from time slice to time slice, one or more constraints may be applied to limit the movement of dynamically placed seams such that any given seam moves gradually over time, limiting potential discontinuities in a visualization of the stitched image on a display. Eye tracking may be used to detect a saccade of a monitored person and/or detect that the monitored person is not looking at the display, and one or more of the constraints used to limit the movement of dynamically placed seams may be relaxed or lifted when the monitored person is experiencing a saccade and/or is looking away from the display.
In various examples, a VPU and associated components may be optimized to improve VPU performance and throughput. For example, the VPU may include a min/max collector, automatic store predication functionality, a SIMD data path organization that allows for inter-lane sharing, a transposed load/store with stride parameter functionality, a load with permute and zero insertion functionality, hardware, logic, and memory layout functionality to allow for two point and two by two point lookups, and per memory bank load caching capabilities. In addition, decoupled accelerators may be used to offload VPU processing tasks to increase throughput and performance, and a hardware sequencer may be included in a DMA system to reduce programming complexity of the VPU and the DMA system. The DMA and VPU may execute a VPU configuration mode that allows the VPU and DMA to operate without a processing controller for performing dynamic region based data movement operations.
G06F 9/30 - Arrangements for executing machine instructions, e.g. instruction decode
G06F 13/28 - Handling requests for interconnection or transfer for access to input/output bus using burst mode transfer, e.g. direct memory access, cycle steal
G06F 15/80 - Architectures of general purpose stored program computers comprising an array of processing units with common control, e.g. single instruction multiple data processors
8.
GENERATING ARTIFICIAL AGENTS FOR REALISTIC MOTION SIMULATION USING BROADCAST VIDEOS
In various examples, artificial intelligence (AI) agents can be generated to synthesize more natural motion by simulated actors in various visualizations (such as video games or simulations). AI agents may employ one or more machine learning models and techniques, such as reinforcement learning, to enable synthesis of motion with enhanced realism. The AI agent can be trained based on widely-available broadcast video data, without the need for more costly and limited motion capture data. To account for the lower quality of such video data, various techniques can be employed, such as taking into account the motion of joints, and applying physics-based constraints on the actors, resulting in higher quality, more lifelike motion.
Apparatuses, systems, and techniques to perform collision-free motion generation (e.g., to operate a real-world or virtual robot). In at least one embodiment, at least a portion of the collision-free motion generation is performed in parallel.
Apparatuses, systems, and techniques to indicate data dependencies. In at least one embodiment, one or more neural networks are used to generate one or more indicators of one or more data dependencies and one or more indicators of direction of the one or more data dependencies.
In various examples, live perception from sensors of a vehicle may be leveraged to detect and classify intersection contention areas 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 outputs—such as signed distance functions—that may correspond to locations of boundaries delineating intersection contention areas. The signed distance functions may be decoded and/or post-processed to determine instance segmentation masks representing locations and classifications of intersection areas or regions. The locations of the intersections areas or regions may be generated in image-space and converted to world-space coordinates to aid an autonomous or semi-autonomous vehicle in navigating intersections according to rules of the road, traffic priority considerations, and/or the like.
G05B 13/02 - Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric
G06F 18/21 - Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
G06T 11/20 - Drawing from basic elements, e.g. lines or circles
G06V 10/26 - Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
G06V 10/34 - Smoothing or thinning of the pattern; Morphological operations; Skeletonisation
G06V 10/44 - Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
G06V 10/82 - Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
G06V 20/56 - Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
G06V 30/262 - Techniques for post-processing, e.g. correcting the recognition result using context analysis, e.g. lexical, syntactic or semantic context
12.
BEHAVIOR-GUIDED PATH PLANNING IN AUTONOMOUS MACHINE APPLICATIONS
In various examples, a machine learning model—such as a deep neural network (DNN)—may be trained to use image data and/or other sensor data as inputs to generate two-dimensional or three-dimensional trajectory points in world space, a vehicle orientation, and/or a vehicle state. For example, sensor data that represents orientation, steering information, and/or speed of a vehicle may be collected and used to automatically generate a trajectory for use as ground truth data for training the DNN. Once deployed, the trajectory points, the vehicle orientation, and/or the vehicle state may be used by a control component (e.g., a vehicle controller) for controlling the vehicle through a physical environment. For example, the control component may use these outputs of the DNN to determine a control profile (e.g., steering, decelerating, and/or accelerating) specific to the vehicle for controlling the vehicle through the physical environment.
Systems and methods herein address momentum conservation in physics engines using one or more processing units to simulate an articulated body based at least on an adjustment to a velocity that is associated with a root link of the articulated body, and using at least a change in momentum determined from one or more external forces separately from a change in momentum determined from one or more internal forces to conserve momentum within the system.
Systems and methods are disclosed related to a convolutional structured state space model (ConvSSM), which has a tensor-structured state but a continuous-time parameterization and linear state updates. The linearity may be exploited to use parallel scans for subquadratic parallelization across the spatiotemporal sequence. The ConvSSM effectively models long-range dependencies and, when followed by a nonlinear operation forms a spatiotemporal layer (ConvS5) that does not require compressing frames into tokens, can be efficiently parallelized across the sequence, provides an unbounded context, and enables fast autoregressive generation.
Apparatuses, systems, and techniques to generate and select grasp proposals. In at least one embodiment, grasp proposals are generated and selected using one or more neural networks, based on, for example, a latent code corresponding to an object.
Pixel depth information is used to determine a weight to apply to neighboring pixels when using a sharpening filter. A difference between neighboring pixel depths is evaluated and pixels with pixel depths that exceed a threshold are given less weight than other pixels. A sharpening mask may be generated using adjusted pixel colors.
Systems and methods estimate occluded pixels in frames of a video sequence. Optical flow data is received to determine a validity for forward and backward flow vectors for a common pixel location in a first frame and a second frame that are temporally next to one another. Occlusion information for the first frame determines pixels that are hidden in the second frame with respect to playback from the first frame to the second frame. Occlusion information for the second frame determines pixels that are hidden in the first frame with respect to playback from the second frame to the first frame.
G06V 10/26 - Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
G06T 7/269 - Analysis of motion using gradient-based methods
G06V 10/56 - Extraction of image or video features relating to colour
G06V 10/60 - Extraction of image or video features relating to illumination properties, e.g. using a reflectance or lighting model
H04N 19/139 - Analysis of motion vectors, e.g. their magnitude, direction, variance or reliability
18.
WIRELESS SIGNAL BEAM MANAGEMENT USING REINFORCEMENT LEARNING
Apparatuses, systems, and techniques to identify and select a wireless signal beam. In at least one embodiment, a wireless signal beam is identified and selected using a determined angle of arrival of one or more wireless signals at a base station or UE.
Systems and methods herein address scalable contact-rich simulation in physics engines using one or more processing units to simulate movement between at least two objects in a simulation, the movement based at least on a plurality of sets of reduced points obtained from an iterative reduction using one or more threshold criteria, the iterative reduction applied to a plurality of points associated with at least one contact between the depictions.
Systems and methods are disclosed for improving natural robustness of sparse neural networks. Pruning a dense neural network may improve inference speed and reduces the memory footprint and energy consumption of the resulting sparse neural network while maintaining a desired level of accuracy. In real-world scenarios in which sparse neural networks deployed in autonomous vehicles perform tasks such as object detection and classification for acquired inputs (images), the neural networks need to be robust to new environments, weather conditions, camera effects, etc. Applying sharpness-aware minimization (SAM) optimization during training of the sparse neural network improves performance for out of distribution (OOD) images compared with using conventional stochastic gradient descent (SGD) optimization. SAM optimizes a neural network to find a flat minimum: a region that both has a small loss value, but that also lies within a region of low loss.
According to an aspect of an embodiment, operations may comprise accessing an HD map of a region comprising information describing an intersection of two or more roads and describing lanes of the two or more roads that intersect the intersection, automatically identifying constraints on the lanes at the intersection, automatically calculating, based on the constraints on the lanes at the intersection, lane connectivity for the intersection, displaying, on a user interface, the automatically calculated lane connectivity for the intersection, receiving, from a user through the user interface, confirmation that the automatically calculated lane connectivity for the intersection is an actual lane connectivity for the intersection, and adding the actual lane connectivity for the intersection to the information describing the intersection in the HD map.
B60W 40/02 - Estimation or calculation of driving parameters for road vehicle drive control systems not related to the control of a particular sub-unit related to ambient conditions
B60W 50/14 - Means for informing the driver, warning the driver or prompting a driver intervention
G01C 21/00 - Navigation; Navigational instruments not provided for in groups
G08G 1/01 - Detecting movement of traffic to be counted or controlled
A method includes receiving, using a processing device, a first condition associated with an operation at a data center, where the operation at the data center pertains to a first location at the data center, the first location corresponding to a first parameter value. The method further includes providing the first condition as an input to a machine learning model. The method also includes performing one or more reinforcement learning techniques using the machine learning model to cause the machine learning model to output an indication of a final location associated with the operation, where the final location corresponds to a final parameter value that is closer to a target than the first parameter value corresponding to the first location at the data center.
H04L 67/60 - Scheduling or organising the servicing of application requests, e.g. requests for application data transmissions using the analysis and optimisation of the required network resources
H04L 41/16 - Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks using machine learning or artificial intelligence
23.
CUSTOMIZING TEXT-TO-SPEECH LANGUAGE MODELS USING ADAPTERS FOR CONVERSATIONAL AI SYSTEMS AND APPLICATIONS
In various examples, one or more text-to-speech machine learning models may be customized or adapted to accommodate new or additional speakers or speaker voices without requiring a full re-training of the models. For example, a base model may be trained on a set of one or more speakers and, after training or deployment, the model may be adapted to support one or more other speakers. To do this, one or more additional layers (e.g., adapter layers) may be added to the model, and the model may be re-trained or updated—e.g., by freezing parameters of the base model while updating parameters of the adapter layers—to generate an adapted model that can support the one or more original speakers of the base model in addition to the one or more additional speakers corresponding to the adapter layers.
G10L 13/00 - Speech synthesis; Text to speech systems
G10L 17/02 - Preprocessing operations, e.g. segment selection; Pattern representation or modelling, e.g. based on linear discriminant analysis [LDA] or principal components; Feature selection or extraction
Machine learning is a process that learns a model from a given dataset, where the model can then be used to make a prediction about new data. In order to reduce the costs associated with collecting and labeling real world datasets for use in training the model, computer processes can synthetically generate datasets which simulate real world data. The present disclosure improves the effectiveness of such synthetic datasets for training machine learning models used in real world applications, in particular by generating a synthetic dataset that is specifically targeted to a specified downstream task (e.g. a particular computer vision task, a particular natural language processing task, etc.).
Apparatuses, systems, and techniques to adapt instructions in a SIMT architecture for execution on serial execution units. In at least one embodiment, a set of one or more threads is selected from a group of active threads associated with an instruction and the instruction is executed for the set of one or more threads on a serial execution unit.
Machine learning is a process that learns a neural network model from a given dataset, where the model can then be used to make a prediction about new data. In order to reduce the size, computation, and latency of a neural network model, a compression technique can be employed which includes model sparsification. To avoid the negative consequences of pruning a fully pretrained neural network model and on the other hand of training a sparse model in the first place without any recovery option, the present disclosure provides a dynamic neural network model sparsification process which allows for recovery of previously pruned parts to improve the quality of the sparse neural network model.
Approaches presented herein provide systems and methods for determining duplicate objects within an interaction environment. Connectivity information for an object may be used to map a set of three linearly independent vectors corresponding to a transform applied to the object. These three linearly independent vectors may be used to form canonical forms of first and second objects to determine whether the first object and the second object are duplicates or near-duplicates. Copies of duplicate or near-duplicate objects may then be deleted from the interaction environment and represented by a common object to which one or more additional transforms are applied.
A remote device utilizes ray tracing to compute a light field for a scene to be rendered, where the light field includes information about light reflected off surfaces within the scene. This light field is then compressed utilizing one or more video compression techniques that implement temporal reuse, such that only differences between the light field for the scene and a light field for a previous scene are compressed. The compressed light field data is then sent to a client device that decompresses the light field data and uses such data to obtain the light field for the scene at the client device. This light field is then used by the client device to compute global illumination for the scene. The global illumination may be used to accurately render the scene at the mobile device, resulting in a realistic scene that is presented by the mobile device.
Apparatuses, systems, and techniques to selectively use one or more neural network layers. In at least one embodiment, one or more neural network layers are selectively used based on, for example, one or more iteratively increasing neural network performance metrics.
In various examples, techniques for using hardware feature trackers in autonomous or semi-autonomous systems are described. Systems and methods are disclosed that use a processor(s) to determine flow vectors associated with pixel locations in a first image. The systems also use the processor(s) to determine a location of a feature point in a second image based at least on one or more of the flow vectors and a subpixel location of the feature point in the first image. In some examples, the processor(s) may include an optical flow accelerator (OFA) that includes a hardware unit storing a lookup table that is used to determine the location of the feature point in the second image. In some examples, the processor(s) may include an OFA to determine the flow vectors and a vision processor to determine the location of the feature point in the second image.
Apparatuses, systems, and techniques including APIs, subscription services, and controllers to enable one or more fifth generation new radio (5G-NR) networks to share information. For example, a processor comprising one or more circuits can perform an API or subscription service to cause a device in a radio access network (RAN) to share its analytic data with a device in a transport network, and said device in said transport network can use said analytic data to adjust its network settings to improve performance.
Apparatuses, systems, and techniques including APIs, subscription services, and controllers to enable one or more fifth generation new radio (5G-NR) networks to share information. For example, a processor comprising one or more circuits can perform an API or subscription service to cause a device in a radio access network (RAN) to share its analytic data with a device in a transport network, and said device in said transport network can use said analytic data to adjust its network settings to improve performance.
Apparatuses, systems, and techniques including APIs, subscription services, and controllers to enable one or more fifth generation new radio (5G-NR) networks to share information. For example, a processor comprising one or more circuits can perform an API or subscription service to cause a device in a radio access network (RAN) to share its analytic data with a device in a transport network, and said device in said transport network can use said analytic data to adjust its network settings to improve performance.
Apparatuses, systems, and techniques including APIs, subscription services, and controllers to enable one or more fifth generation new radio (5G-NR) networks to share information. For example, a processor comprising one or more circuits can perform an API or subscription service to cause a device in a radio access network (RAN) to share its analytic data with a device in a transport network, and said device in said transport network can use said analytic data to adjust its network settings to improve performance.
Apparatuses, systems, and techniques including APIs, subscription services, and controllers to enable one or more fifth generation new radio (5G-NR) networks to share information. For example, a processor comprising one or more circuits can perform an API or subscription service to cause a device in a radio access network (RAN) to share its analytic data with a device in a transport network, and said device in said transport network can use said analytic data to adjust its network settings to improve performance.
Disclosed are apparatuses, systems, and techniques that may use machine learning for implementing speaker recognition, verification, and/or diarization. The techniques include applying a neural network (NN) to a speech data to obtain a speaker embedding representative of an association between the speech data and a speaker that produced the speech. The speech data includes a plurality of frames and a plurality of channels representative of spectral content of the speech data. The NN has one or more blocks of neurons that include a first branch performing convolutions of the speech data across the plurality of channels and across the plurality of frames and a second branch performing convolutions of the speech data across the plurality of channels. Obtained speaker embeddings may be used for various tasks of speaker identification, verification, and/or diarization.
Apparatuses, systems, and techniques including APIs, subscription services, and controllers to enable one or more fifth generation new radio (5G-NR) networks to share information. For example, a processor comprising one or more circuits can perform an API or subscription service to cause a device in a radio access network (RAN) to share its analytic data with a device in a transport network, and said device in said transport network can use said analytic data to adjust its network settings to improve performance.
Apparatuses, systems, and techniques including APIs, subscription services, and controllers to enable one or more fifth generation new radio (5G-NR) networks to share information. For example, a processor comprising one or more circuits can perform an API or subscription service to cause a device in a radio access network (RAN) to share its analytic data with a device in a transport network, and said device in said transport network can use said analytic data to adjust its network settings to improve performance.
H04L 41/5009 - Determining service level performance parameters or violations of service level contracts, e.g. violations of agreed response time or mean time between failures [MTBF]
Apparatuses, systems, and techniques including APIs, subscription services, and controllers to enable one or more fifth generation new radio (5G-NR) networks to share information. For example, a processor comprising one or more circuits can perform an API or subscription service to cause a device in a radio access network (RAN) to share its analytic data with a device in a transport network, and said device in said transport network can use said analytic data to adjust its network settings to improve performance.
Apparatuses, systems, and techniques including APIs, subscription services, and controllers to enable one or more fifth generation new radio (5G-NR) networks to share information.
Apparatuses, systems, and techniques including APIs, subscription services, and controllers to enable one or more fifth generation new radio (5G-NR) networks to share information.
For example, a processor comprising one or more circuits can perform an API or subscription service to cause a device in a radio access network (RAN) to share its analytic data with a device in a transport network, and said device in said transport network can use said analytic data to adjust its network settings to improve performance.
Apparatuses, systems, and techniques including APIs, subscription services, and controllers to enable one or more fifth generation new radio (5G-NR) networks to share information.
Apparatuses, systems, and techniques including APIs, subscription services, and controllers to enable one or more fifth generation new radio (5G-NR) networks to share information.
For example, a processor comprising one or more circuits can perform an API or subscription service to cause a device in a radio access network (RAN) to share its analytic data with a device in a transport network, and said device in said transport network can use said analytic data to adjust its network settings to improve performance.
Apparatuses, systems, and techniques including APIs, subscription services, and controllers to enable one or more fifth generation new radio (5G-NR) networks to share information. For example, a processor comprising one or more circuits can perform an API or subscription service to cause a device in a radio access network (RAN) to share its analytic data with a device in a transport network, and said device in said transport network can use said analytic data to adjust its network settings to improve performance.
Apparatuses, systems, and techniques including APIs, subscription services, and controllers to enable one or more fifth generation new radio (5G-NR) networks to share information. For example, a processor comprising one or more circuits can perform an API or subscription service to cause a device in a radio access network (RAN) to share its analytic data with a device in a transport network, and said device in said transport network can use said analytic data to adjust its network settings to improve performance.
One embodiment of a method for training a first machine learning model having a different architecture than a second machine learning model includes receiving a first data set, performing one or more operations to generate a second data set based on the first data set and the second machine learning model, wherein the second data set includes at least one feature associated with one or more tasks that the second machine learning model was previously trained to perform, and performing one or more operations to train the first machine learning model based on the second data set and the second machine learning model.
In various examples, sensor data may be collected using one or more sensors of an ego-vehicle to generate a representation of an environment surrounding the ego-vehicle. The representation may include lanes of the roadway and object locations within the lanes. The representation of the environment may be provided as input to a longitudinal speed profile identifier, which may project a plurality of longitudinal speed profile candidates onto a target lane. Each of the plurality of longitudinal speed profiles candidates may be evaluated one or more times based on one or more sets of criteria. Using scores from the evaluation, a target gap and a particular longitudinal speed profile from the longitudinal speed profile candidates may be selected. Once the longitudinal speed profile for a target gap has been determined, the system may execute a lane change maneuver according to the longitudinal speed profile.
In various examples, systems and methods are disclosed relating to differentially private generative machine learning models. Systems and methods are disclosed for configuring generative models using privacy criteria, such as differential privacy criteria. The systems and methods can generate outputs representing content using machine learning models, such as diffusion models, that are determined in ways that satisfy differential privacy criteria. The machine learning models can be determined by diffusing the same training data to multiple noise levels.
Denoising images rendered using Monte Carlo sampled ray tracing is an important technique for improving the image quality when low sample counts are used. Ray traced scenes that include volumes in addition to surface geometry are more complex, and noisy when low sample counts are used to render in real-time. Joint neural denoising of surfaces and volumes enables combined volume and surface denoising in real time from low sample count renderings. At least one rendered image is decomposed into volume and surface layers, leveraging spatio-temporal neural denoisers for both the surface and volume components. The individual denoised surface and volume components are composited using learned weights and denoised transmittance. A surface and volume denoiser architecture outperforms current denoisers in scenes containing both surfaces and volumes, and produces temporally stable results at interactive rates.
Various embodiments include techniques for lock-free, unordered in-place compaction of an array. The techniques include receiving a first array that includes a first plurality of data entries, generating a second array that includes a second plurality of data entries, and storing, in the second array, respective index positions of valid data entries included in the first array and invalid data entries included in the first array. The techniques further include determining invalid data entries included in a first portion of the first array based at least on the index positions, determining valid data entries included in a second portion of the first array based at least on the index positions, and replacing contents of the invalid data entries included in the first portion of the first array with contents of the valid data entries included in the second portion of the first array.
In various examples, a two-dimensional (2D) and three-dimensional (3D) deep neural network (DNN) is implemented to fuse 2D and 3D object detection results for classifying objects. For example, regions of interest (ROIs) and/or bounding shapes corresponding thereto may be determined using one or more region proposal networks (RPNs)—such as an image-based RPN and/or a depth-based RPN. Each ROI may be extended into a frustum in 3D world-space, and a point cloud may be filtered to include only points from within the frustum. The remaining points may be voxelated to generate a volume in 3D world space, and the volume may be applied to a 3D DNN to generate one or more vectors. The one or more vectors, in addition to one or more additional vectors generated using a 2D DNN processing image data, may be applied to a classifier network to generate a classification for an object.
G06T 7/521 - Depth or shape recovery from the projection of structured light
G06T 15/00 - 3D [Three Dimensional] image rendering
G06V 10/25 - Determination of region of interest [ROI] or a volume of interest [VOI]
G06V 10/44 - Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
G06V 10/764 - Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
G06V 10/80 - Fusion, i.e. combining data from various sources at the sensor level, preprocessing level, feature extraction level or classification level
G06V 10/82 - Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
G06V 20/58 - Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads
A system includes a first device and a second device coupled to a link having one or more lanes. The first device is to transmit two or more frames to synchronize the one or more data lanes, where each frame comprises a quantity of bits. The second device is to receive a first set of bits from each data lane corresponding to the quantity of bits in each frame of the two or more frames. The second device is to determine that the first set of bits received from a data lane of the one or more data lanes does not correspond to a frame boundary of the two or more frames. The second device is further to synchronize each data lane of the one or more data lanes with respect to the frame boundary, responsive to determining that the first set of bits does not correspond to the frame boundary.
Systems and methods herein address reference frame selection in video streaming applications using one or more processing units to decode a frame of an encoded video stream that uses an inter-frame depicting an object and an intra-frame depicting the object, the intra-frame being included in a set of intra-frames based at least in part on at least one attribute of the object as depicted in the intra-frame being different from the at least one attribute of the object as depicted in other intra-frames of the set of intra-frames.
H04N 19/50 - Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using predictive coding
H04N 19/21 - Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using video object coding with binary alpha-plane coding for video objects, e.g. context-based arithmetic encoding [CAE]
Systems and methods herein address reference frame selection in video streaming applications using one or more processing units to identify a frame of a sequence of frames as a blurred frame based at least in part on a first variance of motion (VoM) of the frame being less than or equal to an adaptive threshold that is based in part on a moving average of variance of motion (MAoV) determined using one or more reference frames.
H04N 19/137 - Motion inside a coding unit, e.g. average field, frame or block difference
H04N 19/186 - Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding characterised by the coding unit, i.e. the structural portion or semantic portion of the video signal being the object or the subject of the adaptive coding the unit being a colour or a chrominance component
Systems and methods relate to facial video encoding and reconstruction, particularly in ultra-low bandwidth settings. In embodiments, a video conferencing or other streaming application uses automatically tracked feature cropping information. A bounding shape size—used to identify the cropped region—varies and is dynamically determined to maintain a proportion for feature reconstruction, such as resizing in the event of a zoom-in on a face (or other feature of interest) or a zoom-out. The tracking scheme may be used to smooth sudden movements, including lateral ones, to generate more natural transitions between frames. Tracking and cropping information (e.g., size and position of the cropped region) may be embedded within an encoded bitstream as supplemental enhancement information (“SEI”), for eventual decoding by a receiver and for compositing a decoded face at a proper location in the applicable stream.
H04N 19/70 - Methods or arrangements for coding, decoding, compressing or decompressing digital video signals characterised by syntax aspects related to video coding, e.g. related to compression standards
G06T 5/50 - Image enhancement or restoration by the use of more than one image, e.g. averaging, subtraction
G06T 7/246 - Analysis of motion using feature-based methods, e.g. the tracking of corners or segments
Systems and methods estimate optical flow vectors for occluded pixels between frames of a video sequence. Regions of occluded pixels may be identified and a cause of their occlusion may be determined. Different estimation techniques may be applied based, at least in part, on the cause of occlusion to provide a lightweight, less resource intensive estimation of optical flow data. Optical flow vectors for pixels that are occluded due to movement out of a frame may be estimated using a first technique while optical flow vectors for pixels that are occluded due to foreground movement may be estimated using a second technique.
G06T 7/269 - Analysis of motion using gradient-based methods
G06V 10/25 - Determination of region of interest [ROI] or a volume of interest [VOI]
G06V 10/26 - Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
H04N 19/132 - Sampling, masking or truncation of coding units, e.g. adaptive resampling, frame skipping, frame interpolation or high-frequency transform coefficient masking
H04N 19/139 - Analysis of motion vectors, e.g. their magnitude, direction, variance or reliability
In various examples, color statistic(s) from ground projections are used to harmonize color between reference and target frames representing an environment. The reference and target frames may be projected onto a representation of the ground (e.g., a ground plane) of the environment, an overlapping region between the projections may be identified, and the portion of each projection that lands in the overlapping region may be taken as a corresponding ground projection. Color statistics (e.g., mean, variance, standard deviation, kurtosis, skew, correlation(s) between color channels) may be computed from the ground projections (or a portion thereof, such as a majority cluster) and used to modify the colors of the target frame to have updated color statistics that match those from the ground projection of the reference frame, thereby harmonizing color across the reference and target frames.
Apparatuses, systems, and techniques to generate computer graphics. In at least one embodiment, an application programming interface call to output an application-generated frame of computer graphics is intercepted. One or more interpolated frames of computer graphics are generated based on the application-generated frames. The application-generated and interpolated frames are output in accordance with a goal rate.
Systems and methods herein address reference frame selection in video streaming applications using one or more processing units to replace, during receipt of an encoded video stream, a first set of frames stored in a cache with a second set of frames based at least in part on an indication within the encoded video stream that the second set of frames includes a non-blurred frame (NBF).
H04N 21/231 - Content storage operation, e.g. caching movies for short term storage, replicating data over plural servers or prioritizing data for deletion
H04N 19/136 - Incoming video signal characteristics or properties
H04N 19/154 - Measured or subjectively estimated visual quality after decoding, e.g. measurement of distortion
H04N 19/172 - Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding characterised by the coding unit, i.e. the structural portion or semantic portion of the video signal being the object or the subject of the adaptive coding the unit being an image region, e.g. an object the region being a picture, frame or field
H04N 19/423 - Methods or arrangements for coding, decoding, compressing or decompressing digital video signals - characterised by implementation details or hardware specially adapted for video compression or decompression, e.g. dedicated software implementation characterised by memory arrangements
H04N 19/70 - Methods or arrangements for coding, decoding, compressing or decompressing digital video signals characterised by syntax aspects related to video coding, e.g. related to compression standards
58.
IDENTIFYING IDLE-CORES IN DATA CENTERS USING MACHINE-LEARNING (ML)
Apparatuses, systems, and techniques to determine a number of idle cores of a computing device using a machine learning (ML) model based on a set of processes executed by the computing device are described. One method determines a set of processes executed by the computing device and determines, using an ML model, a number of cores of the computing device to be powered down based at least on the set of processes. The method updates a first mode of the number of cores to a second mode in which the number of cores consumes less power than in the first mode.
In various examples, color harmonization is applied to images of an environment in a reference light space. For example, different cameras on an ego-object may use independent capturing algorithms to generate processed images of the environment representing a common time slice using different capture configuration parameters. The processed images may be transformed into deprocessed images by inverting one or more stages of image processing to transform the processed images into a reference light space of linear light, and color harmonization may be applied to the deprocessed images in the reference light space. After applying color harmonization, corresponding image processing may be reapplied to the harmonized images using corresponding capture configuration parameters, the resulting processed harmonized images may be stitched into a stitched image, and a visualization of the stitched image may be presented (e.g., on a monitor visible to an occupant or operator of the ego-object).
Systems and methods provide for a machine learning system to train a machine learning model to output a multi-frame blank symbol when processing an auditory input. For example, as the system generates paths through a probability lattice, one or more paths include a multi-frame blank that skips at least one frame associated with the probability lattice. The inclusion of the multi-frame blank symbol may increase a total number of potential paths through the probability lattice, and may allow the machine learning model to more quickly and accurately process audio frames, while disregarding audio frames of less value. In deployment, when an output of the machine learning model indicates a multi-frame blank symbol or token, one or more frames of the auditory input may be omitted from processing.
Various embodiments include a memory device that is capable of performing write training operations. Prior approaches for write training involve storing a long data pattern into the memory followed by reading the long data pattern to determine whether the data was written to memory correctly. Instead, the disclosed memory device stores a first data pattern (e.g., in a FIFO memory within the memory device) or generates the first data pattern (e.g., using PRBS) that is compared with a second data pattern being transmitted to the memory device by an external memory controller. If data patterns match, then the memory device stores a pass status in a register, otherwise a fail status is stored in the register. The memory controller reads the register to determine whether the write training passed or failed.
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.
G01S 7/48 - RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES - Details of systems according to groups , , of systems according to group
G01S 7/481 - Constructional features, e.g. arrangements of optical elements
G01S 17/894 - 3D imaging with simultaneous measurement of time-of-flight at a 2D array of receiver pixels, e.g. time-of-flight cameras or flash lidar
G01S 17/931 - Lidar systems, specially adapted for specific applications for anti-collision purposes of land vehicles
G06V 10/764 - Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
G06V 10/80 - Fusion, i.e. combining data from various sources at the sensor level, preprocessing level, feature extraction level or classification level
G06V 10/82 - Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
G06V 20/58 - Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads
63.
NEURAL NETWORK ACCELERATOR USING LOGARITHMIC-BASED ARITHMETIC
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 to produce partial sums, and multiplying the partial sums by the remainder components to produce a sum. The sum may then be converted back into the logarithmic format.
G06N 3/063 - Physical realisation, i.e. hardware implementation of neural networks, neurons or parts of neurons using electronic means
G06F 7/483 - Computations with numbers represented by a non-linear combination of denominational numbers, e.g. rational numbers, logarithmic number system or floating-point numbers
Apparatuses, systems, and techniques to process image frames. In at least one embodiment, an application programming interface (API) is performed to indicate support to use one or more neural networks to perform frame interpolation.
Apparatuses, systems, and techniques to process image frames. In at least one embodiment, an application programming interface (API) is performed to enable frame interpolation to use one or more neural networks.
Apparatuses, systems, and techniques to process image frames. In at least one embodiment, an application programming interface (API) is performed to indicate frame size information using one or more neural networks.
Various embodiments include techniques for generating topological data for a mesh included in a computer-generated environment. The mesh includes simple geometric shapes, such as triangles. The disclosed techniques identify vertices in the mesh that have the same position and have identical attributes, such as color, normal vector, and texture coordinates. The disclosed techniques further identify vertices in the mesh that have the same position but differ in one or more attributes. The techniques generate lists of the triangles that are adjacent to each vertex included in the mesh. The techniques generate a list of the unique edges included in the mesh. Further, the techniques are well suited for execution on highly parallel processors, such as graphics processing units, thereby reducing the time to generate this topological data. The topological data may then be efficiently used by other computer graphics processing operations.
Techniques are disclosed for improving the throughput of ray intersection or visibility queries performed by a ray tracing hardware accelerator. Throughput is improved, for example, by releasing allocated resources before ray visibility query results are reported by the hardware accelerator. The allocated resources are released when the ray visibility query results can be stored in a compressed format outside of the allocated resources. When reporting the ray visibility query results, the results are reconstructed based on the results stored in the compressed format. The compressed format storage can be used for ray visibility queries that return no intersections or terminate on any hit ray visibility query. One or more individual components of allocated resources can also be independently deallocated based on the type of data to be returned and/or results of the ray visibility query.
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.
G06V 10/25 - Determination of region of interest [ROI] or a volume of interest [VOI]
G06V 10/75 - Image or video pattern matching; Proximity measures in feature spaces using context analysis; Selection of dictionaries
G06V 10/764 - Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
G06V 10/80 - Fusion, i.e. combining data from various sources at the sensor level, preprocessing level, feature extraction level or classification level
G06V 10/82 - Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
G06V 20/56 - Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
G06V 20/70 - Labelling scene content, e.g. deriving syntactic or semantic representations
G08G 1/01 - Detecting movement of traffic to be counted or controlled
Apparatuses, systems, and techniques are presented to remove unintended variations introduced into data. In at least one embodiment, a first image of an object can be generated based, at least in part, upon adding noise to, and removing the noise from, a second image of the object.
Apparatuses, systems, and techniques are presented to generate images representing realistic motion or activity. In at least one embodiment, one or more neural networks are used to select a first neural network to perform a first task based, at least in part, upon a performance estimated by a second neural network.
Techniques are described for detecting an electromagnetic (“EM”) fault injection attack directed toward circuitry in a target digital system. In various embodiments, a first node may be coupled to first driving circuitry, and a second node may be coupled to second driving circuitry. The driving circuitry is implemented in a manner such that a logic state on the second node has greater sensitivity to an EM pulse than has a logic state on the first node. Comparison circuitry may be coupled to the first and to the second nodes to assert an attack detection output responsive to sensing a logic state on the second node that is unexpected relative to a logic state on the first node.
G06F 21/75 - Protecting specific internal or peripheral components, in which the protection of a component leads to protection of the entire computer to assure secure computing or processing of information by inhibiting the analysis of circuitry or operation, e.g. to counteract reverse engineering
G06F 21/52 - Monitoring users, programs or devices to maintain the integrity of platforms, e.g. of processors, firmware or operating systems during program execution, e.g. stack integrity, buffer overflow or preventing unwanted data erasure
Disclosed are apparatuses, systems, and techniques that enable compressed grid-based graph representations for efficient implementations of graph-mapped computing applications. The techniques include but are not limited to selecting a reference grid having a plurality of blocks, assigning nodes of the graph to blocks of the grid, and generating a graph representation that maps directions, relative to the reference grid, of nodal connections of the graph.
Techniques are disclosed herein for designing a circuit. The techniques include receiving a specification for a driver and a plurality of sinks; executing, based on the driver and the plurality of sinks, a machine learning model that predicts at least one of a size, a location, or a delay target of one or more buffers; generating a tree that includes a plurality of nodes representing the driver, the plurality of sinks, and the one or more buffers between the driver and one or more of the sinks; and generating a design of a circuit based on the tree.
Technologies for generating a graphical user interface (GUI) dashboard with a three-dimensional (3D) grid of unit cells are described. An anomaly statistic can be determined for a set of records. A subset of network address identifiers can be identified and sorted according to the anomaly statistic. The subset can have higher anomaly statistics than other network address identifiers. There can be a maximum number in the subset. The GUI dashboard is generated with unit cells organized by the subset of network address identifiers as rows, time intervals as columns, colors as a configurable anomaly score indicator, and a number of network access events as column heights. Each unit cell is a colored, 3D visual object representing a composite score of anomaly scores associated with zero or more network access events corresponding to the respective network address identifier at the respective time interval. The GUI dashboard is rendered on a display.
G06F 3/04845 - Interaction techniques based on graphical user interfaces [GUI] for the control of specific functions or operations, e.g. selecting or manipulating an object, an image or a displayed text element, setting a parameter value or selecting a range for image manipulation, e.g. dragging, rotation, expansion or change of colour
One embodiment of a display system includes one or more light sources, one or more spatial light modulators, and a plurality of scatterers. One embodiment of a method for displaying content includes computing at least one of a phase or an amplitude modulation associated with two-dimensional (2D) or three-dimensional (3D) content, and causing one or more spatial light modulators to modulate light based on the at least one of a phase or an amplitude modulation to generate modulated light, where the modulated light is scattered by a plurality of scatterers.
One embodiment of a method for generating representations of scenes includes assigning each image included in a set of images of a scene to one or more clusters of images based on a camera pose associated with the image, and performing one or more operations to generate, for each cluster included in the one or more clusters, a corresponding three-dimensional (3D) representation of the scene based on one or more images assigned to the cluster.
Systems techniques to control a robot are described herein. In at least one embodiment, a machine learning model for controlling a robot is trained based at least on one or more population-based training operations or one or more reinforcement learning operations. Once trained, the machine learning model can be deployed and used to control a robot to perform a task.
Various embodiments include techniques for performing parallel edge decimation on a high resolution mesh by collapsing multiple edges in parallel by blocking only the neighbor edges of the edges selected as collapse candidates. Effectively, the disclosed techniques dynamically partition the mesh into small partitions around the collapse candidates. In this manner, the techniques identify all the edges that may be independently collapsed in a single, now parallel, iteration. Edge decimation may be performed so that certain computational geometry techniques can be efficiently applied to a simpler mesh. In so doing, the disclosed techniques preserve the history of how the edge decimation process displaces the vertices of the original mesh to generate the simplified mesh. As a result, the results of the computational geometry techniques as applied to the simplified mesh can be propagated back to the original mesh.
A method for generating, by an encoder-based model, a three-dimensional (3D) representation of a two-dimensional (2D) image is provided. The encoder-based model is trained to infer the 3D representation using a synthetic training data set generated by a pre-trained model. The pre-trained model is a 3D generative model that produces a 3D representation and a corresponding 2D rendering, which can be used to train a separate encoder-based model for downstream tasks like estimating a triplane representation, neural radiance field, mesh, depth map, 3D key points, or the like, given a single input image, using the pseudo ground truth 3D synthetic training data set. In a particular embodiment, the encoder-based model is trained to predict a triplane representation of the input image, which can then be rendered by a volume renderer according to pose information to generate an output image of the 3D scene from the corresponding viewpoint.
In various examples, sensor parameter calibration techniques for in-cabin monitoring systems and applications are presented. An occupant monitoring system (OMS) is an example of a system that may be used within a vehicle or machine cabin to perform real-time assessments of driver and occupant presence, gaze, alertness, and/or other conditions. In some embodiments, a calibration parameter for an interior image sensor is determined so that the coordinates of features detected in 2D captured images may be referenced to an in-cabin 3D coordinate system. In some embodiments, a processing unit may detect fiducial points using an image of an interior space captured by a sensor, determine a 2D image coordinate for a fiducial point using the image, determine a 3D coordinate for the fiducial point, determine a calibration parameter comprising a rotation-translation transform from the 2D image coordinate and the 3D coordinate, and configure an operation based on the calibration parameter.
In various examples, calibration techniques for interior depth sensors and image sensors for in-cabin monitoring systems and applications are provided. An intermediary coordinate system may be generated using calibration targets distributed within an interior space to reference 3D positions of features detected by both depth-perception and optical image sensors. Rotation-translation transforms may be determined to compute a first transform (H1) between the depth-perception sensor's 3D coordinate system and the 3D intermediary coordinate system, and a second transform (H2) between the optical image sensor's 2D coordinate system and the intermediary coordinate system. A third transform (H3) between the depth-perception sensor's 3D coordinate system and the optical image sensor's 2D coordinate system can be computed as a function of H1 and H2. The calibration targets may comprise a structural substrate that includes one or more fiducial point markers and one or more motion targets.
G06V 10/24 - Aligning, centring, orientation detection or correction of the image
B60W 40/02 - Estimation or calculation of driving parameters for road vehicle drive control systems not related to the control of a particular sub-unit related to ambient conditions
G06T 3/60 - Rotation of a whole image or part thereof
A receiver device includes detection logic, error counter logic, and threshold logic. The detection detects frame errors in data frames received by a transmitter device. The error counter logic increments a first value of an error count responsive to each error signal, indicative of a frame error in a data frame, received from the detection logic. The error counter logic reduces the first value to a second value (non-zero value) for the error count responsive to receiving a decrement signal and a period marker signal corresponding to a programmable period. The error counter logic resets the first value or the second value of the error count to zero responsive to receiving a reset signal. The threshold logic compares a current value of the error count with a threshold number of frame errors and output an interrupt responsive to the current value satisfying the threshold number of frame errors.
Apparatuses, systems, and techniques to process image frames. In at least one embodiment, an application programming interface (API) is performed to disable frame interpolation to use one or more neural networks.
Approaches for addressing issues associated with processing workloads that exhibit high divergence in execution and data access are provided. A plurality of workload items to be processed at least partially in parallel may be identified. Coherence information associated with the plurality of workload items may be determined. The plurality of workload items may be enqueued in a segmented queue. The plurality of workload items may be sorted based at least on a similarity of the coherence information. The sorted plurality of workload items may be stored to the queue. Using a set of processing units, the workload items in the queue may be processed at least partially in parallel according to an order of the sorting.
Disclosed are apparatuses, systems, and techniques that may use machine learning for determining transmitted signals in communication systems that deploy orthogonal frequency division multiplexing. A system for performing the disclosed techniques includes receiving (RX) antennas to receive RX signals, each RX signal received over a respective resource element of a resource grid. Individual resource elements of the resource grid are associated with different radio subcarriers and/or data symbols. The RX signals include a combination of a plurality of transmitted (TX) streams. The system further includes a processing device to process the RX signals using one or more neural network models to determine TX data symbols transmitted via the plurality of TX streams.
Technologies for generating a set of models for each account, where each model is a fine-grained, unsupervised behavior model trained for each user to monitor and detect anomalous patterns are described. An unsupervised training pipeline can generate user models, each being associated with one of multiple accounts and is trained to detect an anomalous pattern using feature data associated with the one account. Each account is associated with at least one of a user, a machine, or a service. An inference pipeline can detect a first anomalous pattern in first data associated with a first account using a first user model. The inference pipeline can detect a second anomalous pattern in second data associated with a second account using a second user model.
Systems and methods are disclosed that relate to freespace detection using machine learning models. First data that may include object labels may be obtained from a first sensor and freespace may be identified using the first data and the object labels. The first data may be annotated to include freespace labels that correspond to freespace within an operational environment. Freespace annotated data may be generated by combining the one or more freespace labels with second data obtained from a second sensor, with the freespace annotated data corresponding to a viewable area in the operational environment. The viewable area may be determined by tracing one or more rays from the second sensor within the field of view of the second sensor relative to the first data. The freespace annotated data may be input into a machine learning model to train the machine learning model to detect freespace using the second data.
In various examples, the decoding and upscaling capabilities of a client device are analyzed to determine encoding parameters and operations used by a content streaming server to generate encoded video streams. The quality of the upscaled content of the client device may be monitored by the streaming servers such that the encoding parameters may be updated based on the monitored quality. In this way, the encoding operations of one or more streaming servers may be more effectively matched to the decoding and upscaling abilities of one or more client devise such that an increased number of client devices may be served by the streaming servers.
H04N 19/59 - Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using predictive coding involving spatial sub-sampling or interpolation, e.g. alteration of picture size or resolution
H04N 19/105 - Selection of the reference unit for prediction within a chosen coding or prediction mode, e.g. adaptive choice of position and number of pixels used for prediction
H04N 19/146 - Data rate or code amount at the encoder output
Apparatuses, systems, and techniques to cause one or more neural networks to be trained. In at least one embodiment, a processor includes one or more circuits to cause one or more neural networks to be trained based, at least in part, on one or more capabilities.
G06N 3/04 - Architecture, e.g. interconnection topology
H04L 41/16 - Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks using machine learning or artificial intelligence
Apparatuses, systems, and techniques to generate animations. In at least one embodiment, one or more neural networks control motion of one or more animated objects based, at least in part, on natural language inputs.
Apparatuses, systems, and techniques to optimize processor performance. In at least one embodiment, a processor is to perform an application programming interface (API) to exclude one or more portions of program code from a program.
Apparatuses, systems, and techniques to perform versions of program code. In at least one embodiment, one or more versions of a plurality of versions of software code are performed. In at least one embodiment, one or more versions of a plurality of versions of software code are performed based, at least in part, on whether the versions of the program code access overlapping memory regions.
Apparatuses, systems, and techniques to optimize processor performance. In at least one embodiment, a method increases an operation voltage of one or more processors, based at least in part, on one or more error rates of the one or more processors.
Apparatuses, systems, and techniques to select one or more beams to transmit signals. In at least one embodiment, a system includes one or more circuits to select one or more wireless signal beams based, at least in part, on measuring one or more received reference signals.
H04B 7/08 - Diversity systems; Multi-antenna systems, i.e. transmission or reception using multiple antennas using two or more spaced independent antennas at the receiving station
96.
REFERENCE SIGNAL CONFIGURATION INFORMATION TRANSMISSION
Apparatuses, systems, and techniques to transmit configuration information. In at least one embodiment, a processor includes one or more circuits to wirelessly transmit reference signal configuration information corresponding to one or more reference signals.
Apparatuses, systems, and techniques are presented to generate digital content. In at least one embodiment, one or more neural networks are used to generate one or more textured three-dimensional meshes corresponding to one or more objects based, at least in part, one or more two-dimensional images of the one or more objects.
A circuit for improving control over asynchronous signal crossings during circuit scan tests includes multiple scan registers and a decoder configured to translate a combined output of the scan registers into multiple one-hot controls to the local clock gates of scan registers disposed in multiple different clock domains. Programmable registers are provided to selectively enable and disable the local clock gates of the different clock domains.
Techniques applicable to a ray tracing hardware accelerator for traversing a hierarchical acceleration structure with reduced false positive ray intersections are disclosed. The reduction of false positives may be based upon one or more of selectively performing a secondary higher precision intersection test for a bounding volume, identifying and culling bounding volumes that degenerate to a point, and parametrically clipping rays that exceed certain configured distance thresholds.
Techniques applicable to a ray tracing hardware accelerator for traversing a hierarchical acceleration structure with reduced false positive ray intersections are disclosed. The reduction of false positives may be based upon one or more of selectively performing a secondary higher precision intersection test for a bounding volume, identifying and culling bounding volumes that degenerate to a point, and parametrically clipping rays that exceed certain configured distance thresholds.
patents
