ELUCIDATED NATURAL LANGUAGE ARTIFACT RECOMBINATION WITH CONTEXTUAL AWARENESS
Granted: February 15, 2024
Application Number:
20240054282
An embodiment includes identifying, from among the plurality of digital content datasets, a set of candidate textual items based on relevance to a specified subtopic using one or more natural language processing techniques. The embodiment groups candidate textual items into a predetermined number of groups using relevance scores and feature vectors. The embodiment trains a pre-trained encoder-decoder model using a designated group of selected textual items, where the pre-trained…
OPERATOR MIRRORING
Granted: February 15, 2024
Application Number:
20240053984
At a mirrored operator, a current operand snapshot is received from a source operator. The current operand snapshot comprises configuration data of a set of source operands managed by the source operator, and the set of source operands comprises at least one source operand. A set of mirrored operands is configured by the mirrored operator according to the current operand snapshot, resulting in a first configuration of the set of mirrored operands. At the mirrored operator, a change…
PRIVATE VERTICAL FEDERATED LEARNING
Granted: February 1, 2024
Application Number:
20240039692
A second set of data identifiers, comprising identifiers of data usable in federated model training by a second data owner, is received at a first data owner from the second data owner. An intersection set of data identifiers is determined at the first data owner. At the first data owner according to the intersection set of data identifiers, the data usable in federated model training is rearranged by the first data owner to result in a first training dataset. At the first data owner…
VISUAL REPRESENTATION FOR HIGHER DIMENSION DATA SETS
Granted: February 1, 2024
Application Number:
20240037321
A method for adding dimensions to a visual representation is disclosed. In one embodiment, such a method obtains a data set containing data in a plurality of rows and columns (i.e., dimensions). The method divides the dimensions into a plurality of groups and determines a coordinate system for each group. For each row in the data set, the method determines data points for each group in the corresponding coordinate system. The method then connects the data points for each row with lines…
PRIVATE VERTICAL FEDERATED LEARNING
Granted: February 1, 2024
Application Number:
20240039692
A second set of data identifiers, comprising identifiers of data usable in federated model training by a second data owner, is received at a first data owner from the second data owner. An intersection set of data identifiers is determined at the first data owner. At the first data owner according to the intersection set of data identifiers, the data usable in federated model training is rearranged by the first data owner to result in a first training dataset. At the first data owner…
VISUAL REPRESENTATION FOR HIGHER DIMENSION DATA SETS
Granted: February 1, 2024
Application Number:
20240037321
A method for adding dimensions to a visual representation is disclosed. In one embodiment, such a method obtains a data set containing data in a plurality of rows and columns (i.e., dimensions). The method divides the dimensions into a plurality of groups and determines a coordinate system for each group. For each row in the data set, the method determines data points for each group in the corresponding coordinate system. The method then connects the data points for each row with lines…
VIRTUAL FIELD OF VIEW ADJUSTMENT IN LIVE VOLUMETRIC VIDEO
Granted: January 25, 2024
Application Number:
20240031519
Video of a plurality of fields of view of a scene is captured, each field of view comprising data of the scene from a different vantage point. An excitement level is determined by analyzing a portion of the captured video. Using the excitement level, a time series of future excitement levels is forecast. Using the time series of future excitement levels, a virtual field of view path of the scene is forecast. An insert image is determined to be included in the virtual field of view path.…
SYNCHRONIZING PHYSICAL AND VIRTUAL ENVIRONMENTS USING QUANTUM ENTANGLEMENT
Granted: January 25, 2024
Application Number:
20240029375
An embodiment includes accessing captured video of a first physical object in a physical environment. The embodiment also includes detecting a feature of the first physical object in a first frame of the video. The embodiment encodes a first qubit with a first quantum state based on a first value of the feature of the first physical object, and then entangles the first qubit with a second qubit forming an entangled qubit pair. The embodiment detects a second quantum state of the second…
STICKIFICATION USING ANYWHERE PADDING TO ACCELERATE DATA MANIPULATION
Granted: January 25, 2024
Application Number:
20240028899
Embodiments are provided for efficient realization of memory-bound operations in a computing system by a processor. Data may be read from and written to a memory at a granular level using a stickification operation. One or more regions of activation and weight tensor data on the memory may be annotated by coupling the stickification operation with padding.
ACCELERATED ENCODING FOR VIRTUAL MACHINE SYNCHRONIZATION
Granted: January 25, 2024
Application Number:
20240028364
An embodiment includes a virtual machine (VM) memory synchronization process for improved failure tolerance. The process includes writing, by an intelligent memory controller (IMC), current snapshot data to a first series of contiguous memory addresses, where the current snapshot data is received by the IMC from a memory of an active VM via a direct memory access (DMA) transfer operation. The IMC executes concurrent threads associated with respective spans of the contiguous memory…
ACCELERATED ENCODING FOR VIRTUAL MACHINE SYNCHRONIZATION
Granted: January 25, 2024
Application Number:
20240028364
An embodiment includes a virtual machine (VM) memory synchronization process for improved failure tolerance. The process includes writing, by an intelligent memory controller (IMC), current snapshot data to a first series of contiguous memory addresses, where the current snapshot data is received by the IMC from a memory of an active VM via a direct memory access (DMA) transfer operation. The IMC executes concurrent threads associated with respective spans of the contiguous memory…
STICKIFICATION USING ANYWHERE PADDING TO ACCELERATE DATA MANIPULATION
Granted: January 25, 2024
Application Number:
20240028899
Embodiments are provided for efficient realization of memory-bound operations in a computing system by a processor. Data may be read from and written to a memory at a granular level using a stickification operation. One or more regions of activation and weight tensor data on the memory may be annotated by coupling the stickification operation with padding.
SYNCHRONIZING PHYSICAL AND VIRTUAL ENVIRONMENTS USING QUANTUM ENTANGLEMENT
Granted: January 25, 2024
Application Number:
20240029375
An embodiment includes accessing captured video of a first physical object in a physical environment. The embodiment also includes detecting a feature of the first physical object in a first frame of the video. The embodiment encodes a first qubit with a first quantum state based on a first value of the feature of the first physical object, and then entangles the first qubit with a second qubit forming an entangled qubit pair. The embodiment detects a second quantum state of the second…
VIRTUAL FIELD OF VIEW ADJUSTMENT IN LIVE VOLUMETRIC VIDEO
Granted: January 25, 2024
Application Number:
20240031519
Video of a plurality of fields of view of a scene is captured, each field of view comprising data of the scene from a different vantage point. An excitement level is determined by analyzing a portion of the captured video. Using the excitement level, a time series of future excitement levels is forecast. Using the time series of future excitement levels, a virtual field of view path of the scene is forecast. An insert image is determined to be included in the virtual field of view path.…
PREVENTING JITTER IN HIGH PERFORMANCE COMPUTING SYSTEMS
Granted: January 18, 2024
Application Number:
20240020172
A first device may obtain metrics information associated with a second device, the metrics information indicating a measurement of a performance of a component of the second device, and the metrics information being obtained via a first network. The first device may determine a load of a processing unit of the second device based on the metrics information. The first device may determine, based on the load of the processing unit, whether the second device is capable of executing a…
TRAINING A NEURAL NETWORK USING AN ACCELERATED GRADIENT WITH SHUFFLING
Granted: January 18, 2024
Application Number:
20240020528
An index sequence specifying an index of training data corresponding to a component of a cost function is generated. A first model parameter in the set of model parameters is set to an initial value. Using the index sequence, a neural network model comprising a set of weights is trained. As part of the training, using the index sequence, a learning rate, and a set of gradients, a subset of the set of model parameters is updated. As part of the training, a momentum term is set. As part of…
TRAINING A NEURAL NETWORK USING AN ACCELERATED GRADIENT WITH SHUFFLING
Granted: January 18, 2024
Application Number:
20240020528
An index sequence specifying an index of training data corresponding to a component of a cost function is generated. A first model parameter in the set of model parameters is set to an initial value. Using the index sequence, a neural network model comprising a set of weights is trained. As part of the training, using the index sequence, a learning rate, and a set of gradients, a subset of the set of model parameters is updated. As part of the training, a momentum term is set. As part of…
PREVENTING JITTER IN HIGH PERFORMANCE COMPUTING SYSTEMS
Granted: January 18, 2024
Application Number:
20240020172
A first device may obtain metrics information associated with a second device, the metrics information indicating a measurement of a performance of a component of the second device, and the metrics information being obtained via a first network. The first device may determine a load of a processing unit of the second device based on the metrics information. The first device may determine, based on the load of the processing unit, whether the second device is capable of executing a…
PROVIDING A SEMANTIC ENCODING AND LANGUAGE NEURAL NETWORK
Granted: January 11, 2024
Application Number:
20240013003
Embodiments are provided for unsupervised learning of domain specific knowledge graph from textual data and language generation from knowledge graph via reinforcement learning in a computing system by a processor. Unstructured data is automatically parsed into one or more knowledge graphs based on the unstructured data and a list of candidate relations using a first machine learning model. Text data is generated from the one or more knowledge graphs using a second machine learning model.
PROVIDING A SEMANTIC ENCODING AND LANGUAGE NEURAL NETWORK
Granted: January 11, 2024
Application Number:
20240013003
Embodiments are provided for unsupervised learning of domain specific knowledge graph from textual data and language generation from knowledge graph via reinforcement learning in a computing system by a processor. Unstructured data is automatically parsed into one or more knowledge graphs based on the unstructured data and a list of candidate relations using a first machine learning model. Text data is generated from the one or more knowledge graphs using a second machine learning model.
