Alerta

DEEP NEURAL NETWORK INFERENCE METHOD BASED ON IDLE CPU RESOURCE FOR MAXIMIZING RESOURCE UTILIZATION RATE IN TRAINING CLUSTER

Resumen de: WO2025143765A1

A deep neural network inference method based on an idle CPU resource according to the present specification may comprise the steps of: when a training task is reserved and all GPUs are used, classifying a CPU core into a training task-specific group, and classifying an unallocated idle CPU core into an unallocated group (U group); executing a training task by using a CPU core of the training task-specific group and, when there is a request for an online inference task, executing the online inference task by using the idle CPU core of the U group; and when there is a request for a batch inference task, additionally executing the batch inference task by using at least one of the idle CPU core of the U group and an idle CPU core of the training task-specific group.

Data-Driven State Estimation and System Control under Uncertainty

Resumen de: US2025216824A1

A control method for controlling an electro-mechanical system according to a task estimates the state of the system using an adaptive surrogate model of the system to produce an estimation of the state of the system. The adaptive surrogate model includes a neural network employing a weighted combination of neural ODEs of dynamics of the system in latent space, such that weights of the weighted combination of neural ODEs represent the uncertainty. The method controls the system according to the task based on the estimation of the state of the system and tunes the weights of the weighted combination of neural ODEs based on the controlling.

METHOD AND SYSTEM FOR AUGMENTED SPEECH EMBEDDINGS BASED AUTOMATIC SPEECH RECOGNITION

Resumen de: US2025218451A1

Though several data augmentation techniques have been explored in the signal or feature space, very few studies have explored augmentation in the embedding space for Automatic Speech Recognition (ASR). The outputs of the hidden layers of a neural network can be seen as different representations or projections of the features. The augmentations performed on the features may not necessarily translate into augmentation of the different projections of the features as obtained from the output of the hidden layers. To overcome the challenges of the conventional approaches, embodiments herein provide a method and system for augmented speech embeddings based automatic speech recognition. The present disclosure provides an augmentation scheme which works on the speech embeddings. The augmentation works by replacing a set of randomly selected embeddings by noise during training. It does not require additional data, works online during training, and adds very little to the overall computational cost.

METHOD OF OPERATING ARTIFICIAL NEURAL NETWORK AND STORAGE DEVICE PERFORMING THE SAME

Resumen de: US2025209315A1

A method of operating an artificial neural network model including a plurality of nodes includes: dividing the artificial neural network model into a divided artificial neural network including plurality node groups using a first grouping manner, allocating the plurality of node groups to a plurality of first hardware accelerators and a plurality of second hardware accelerators using a first corresponding manner to generate an allocation, executing the divided artificial neural network model on a plurality of input values to generate a plurality of inference results values, for each of the plurality of inference result values, recording activation area information of the plurality of node groups and a call count, and performing at least one of a first operation to change the allocation and a second operation to change the divided artificial neural network based on the activation area information and the call count.

SATELLITE OPTIMIZATION MANAGEMENT SYSTEM BASED ON NATURAL LANGUAGE INPUT AND ARTIFICIAL INTELLIGENCE

Resumen de: US2025219718A1

Satellite optimization management systems based on natural language input and artificial intelligence methods are provided. Conventional satellite management systems require understanding how to control and program satellites. As the number of satellites are deployed, the need to control such satellites by natural language instruction increases. The systems and methods disclosed herein include a natural language processing module configured to receive and interpret user input expressed in natural language to determine a user's intent and map it to specific tasks. In order to correctly determine a user's intent, a neural network with artificial intelligence models may be used. Such user's intent may be used to generate and execute satellite command sequences based on operational tasks derived from the user's natural language inputs. Such natural language input and derived intents can be translated into command sequences to that are applicable across an entire constellation of a large number of satellites.

SYSTEMS AND METHODS FOR A LARGE LANGUAGE MODEL-BASED SAFE USAGE PLAN GENERATOR FOR HUMAN-IN-THE-LOOP CYBER-PHYSICAL SYSTEMS

Resumen de: US2025217539A1

Example implementations of a neural network implementing a large language model for generating action plans that align with physical system dynamics of a cyber-physical system (CPS) but are also safe for the human users are disclosed. Examples include a physical dynamics coefficient estimator based on a liquid time constant neural network that can derive coefficients of dynamical models with some unmeasured state variables. Further, the model coefficients are then used to train an LLM with prompts embodied with traces from dynamical system and the corresponding model coefficients. When integrated with a contextualized chatbot, feasible and safe plans can be generated to manage external events such as meals for automated insulin delivery systems used by Type 1 Diabetes subjects.

EDGE DEVICE FOR COLLABORATIVE INFERENCE BASED ON SEMANTIC COMMUNICATIONS AND METHOD THEREOF

Resumen de: US2025217674A1

A collaborative inference method based on semantic communications may include acquiring input data by an edge device, performing a first inference on the input data by using a weak machine learning model by the edge device, computing an uncertainty of the inference result by the edge device, extracting semantic information from the input data by the edge device when the uncertainty is greater than or equal to a threshold value, and requesting a second inference by transmitting the semantic information, rather than the entire input data, to a server by the edge device. The edge device may perform the first inference using a first artificial neural network with the weak machine learning model, and the server may perform the second inference using a second artificial neural network with a strong machine learning model. The method can reduce processing latency and bandwidth consumption while enhancing accuracy and computing efficiency.

DATA PROCESSING METHOD, ELECTRONIC DEVICE, AND STORAGE MEDIUM

Resumen de: US2025217677A1

A data processing method, an electronic device, and a storage medium. The data processing method is applied to a compiled neural network model, a compiled computation graph corresponding to the neural network model includes M fusion computing nodes, M is a positive integer, and the data processing method includes: packaging data in a plurality of input data groups to obtain at least one instance input data, wherein each instance input data at least includes data required by at least one of M fusion computing nodes when the neural network model executes one-time model inference; reading one instance input data of the at least one instance input data; based on the instance input data, executing an execution instruction corresponding to at least one fusion computing node, to obtain an output of the at least one fusion computing node; and outputting the output of the at least one fusion computing node.

FEATURE-BASED OBJECT IDENTIFICATION FOR AUTONOMOUS SYSTEMS AND APPLICATIONS

Resumen de: US2025218195A1

In various examples, live perception from sensors of a vehicle may be leveraged to generate object tracking paths for the vehicle to facilitate navigational controls in real-time or near real-time. For example, a deep neural network (DNN) may be trained to compute various outputs-such as feature descriptor maps including feature descriptor vectors corresponding to objects included in a sensor(s) field of view. The outputs may be decoded and/or otherwise post-processed to reconstruct object tracking and to determine proposed or potential paths for navigating the vehicle.

Defect Detection, Mesh Cleanup, and Mesh Cleanup Validation in Digital Dentistry

Nº publicación: US2025217663A1 03/07/2025

Solicitante:

SOLVENTUM INTELLECTUAL PROPERTIES COMPANY [US]
Solventum Intellectual Properties Company

Resumen de: US2025217663A1

Systems and techniques for training one or more neural networks to automatically identify one or more aspects of a digital representation used in digital oral care are disclosed including identifying one or more aspects of the first digital representation for which additional processing is to be performed, based on a list of 3D elements, generating a predicted representation by labeling those one or more aspects for which additional processing is to be performed, generating an accuracy score that specifies a difference between the one or more predicted representations and one or more respective reference representations that identify the one or more aspects of the first digital representation for which additional processing is to be performed, and modifying at least one aspect of the neural network based on the accuracy score.