Alerta

EXPLOITING INPUT DATA SPARSITY IN NEURAL NETWORK COMPUTE UNITS

Absstract of: EP4793824A2

0001 A hardware circuit for implementing a neural network comprising a plurality of neural network layers comprises a controller. The controller is configured to analyze output activations computed by a first compute system for a first neural network layer, where the output activations are provided on an output activation bus. The controller is further configured to determine which of the output activations have a non-zero value, generate an additional representation of the output activations that identifies only the output activations having a non-zero value, and use the additional representation to supply only the output activations having a non-zero value as input activations to a subsequent, second compute system for a second neural network layer.

DATA PROCESSING METHOD AND APPARATUS BASED ON MULTI-MODAL FUSION

Absstract of: EP4793799A1

The present application provides a data processing method and apparatus based on multimodal fusion, pertaining to the technical field of data processing, where the method includes: acquiring one-dimensional data and image data; converting the one-dimensional data into two-dimensional data based on a dimension of the image data; performing zero-padding processing on vacant positions in the two-dimensional data; performing stacking processing on the zero-padded two-dimensional data and the image data to obtain a multilayer stacked input feature map; performing fusion processing on the multilayer stacked input feature map through a neural network to obtain a fused feature map; and performing data processing based on the fused feature map. The present invention can unify the data formats of different modalities, enabling them to be processed in the same feature space, significantly simplifying the alignment process between heterogeneous data.

IMAGE PROCESSING DEVICE AND OPERATION METHOD THEREFOR

Absstract of: EP4793878A1

Provided are an image processing device and an operating method of the same. The image processing device includes a memory storing one or more instructions, and at least one processor including processing circuitry, and memory storing one or more instructions that, when executed by the at least one processor individually or collectively, cause the image processing device to obtain a neural network model corresponding to a quality of an input image and viewing information related to the input image. The at least one processor is configured to generate training data, based on the quality of the input image and the viewing information. The at least one processor is configured to train the neural network model by using the training data. The at least one processor is configured to obtain an image quality processed output image from the input image, based on the trained neural network model.

METHOD AND SYSTEM FOR PROFILING PARTICLES IN TAXAS

Absstract of: EP4793908A1

0001 Disclosed is a computer-implemented method for profiling particles in a taxa using a sequence of input data images. The process involves identifying and categorizing suspended particles in each image to obtain bounding boxes and classification data. These particles are then tracked across subsequent images using the bounding boxes to compile tracking data. The method uses this data to output a profile of the suspended particles, incorporating taxonomic identification and possibly using convolutional operations. It employs two neural networks: one for identifying regions of interest and another for categorizing the particles based on these regions. The profile may include biomass calculations and assessments of ecosystem status, integrating sensor metadata such as depth, chlorophyll-a, salinity, and temperature. Non-particle elements like bubbles and damaged areas are excluded from tracking. The method also encompasses a system setup with a camera and processor, and a computer program that enables the execution of these methods.

TRAINING METHOD AND APPARATUS, VEHICLE SAFETY FUNCTION CONTROL METHOD AND APPARATUS, AND VEHICLE

Absstract of: EP4793797A1

The present disclosure relates to the field of control, and provides a training method and apparatus, a vehicle safety function control method and apparatus, and a vehicle. The training method comprises : acquiring a signal sample image of a vehicle, wherein the signal sample image comprises a safety function normal image and a safety function failure image; using the signal sample image to train a deep neural network model, and using the trained deep neural network model to perform data augmentation processing on the signal sample image to obtain training sample images; and using the training sample images to train a safety function failure identification classifier, wherein the safety function failure identification classifier is used for identifying a safety function state during vehicle operation, and the safety function state includes a safety function normal state or a safety function failure state.

ELECTRONIC APPARATUS AND METHOD FOR CONTROLLING THEREOF

Absstract of: EP4793903A2

A method of controlling an electronic apparatus includes acquiring an image and depth information of the acquired image; inputting the acquired image into a neural network model trained to acquire information on objects included in the acquired image; acquiring an intermediate feature value output by an intermediate layer of the neural network model; identifying a feature area for at least one object among the objects included in the acquired image based on the intermediate feature value; and acquiring distance information between the electronic apparatus and the at least one object based on the feature area for the at least one object and the depth information.

SUBJECT-DRIVEN DIFFUSION NEURAL NETWORKS

Absstract of: US20260237019A1

0000 Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating images of a new subject using a diffusion neural network.

NEURAL NETWORKS WITH SUBDOMAIN TRAINING

Absstract of: US20260236778A1

0000 Heterogenous neural networks are disclosed that have activation functions that hold multi-variable equations. These variables can be passed from one neuron to another. The neurons may be laid out in a topologically similar fashion to a physical system that the heterogenous neural network is modeling. A neural network may have inputs of more than one type. Only a portion of the inputs (a subdomain) may be optimized In such an instance, the neural network may run forward, backpropagate to all inputs, and then perform optimization only on those inputs which will be optimized.

TECHNIQUE TO PERFORM NEURAL NETWORK ARCHITECTURE SEARCH WITH FEDERATED LEARNING

Absstract of: US20260236742A1

Apparatuses, systems, and techniques to select a neural network architecture from a plurality of neural networks in a federated learning (FL) setting. In at least one embodiment, a neural network is trained by combining training results from different FL computing systems, where each of the different FL computing systems, for example, trains different portions of the neural network.

CLASS AGNOSTIC OBJECT MASK GENERATION

Absstract of: US20260237074A1

Class agnostic object mask generation uses a vision transformer-based auto-labeling framework requiring only images and object bounding boxes to generate object (segmentation) masks. The generated object masks, images, and object labels may then be used to train instance segmentation models or other neural networks to localize and segment objects with pixel-level accuracy.

THREE-DIMENSIONAL BASE CALLING IN NEXT GENERATION SEQUENCING ANALYSIS

Absstract of: AU2025214687A1

Disclosed herein are sequencing systems and sequencing methods for training neural networks and for utilizing the trained neural networks for sequencing analysis after acquiring flow cell images using the sequencing systems. The sequencing systems disclosed herein can include Field-Programmable Gate Array (FPGAs), artificial intelligence (AI) chips, or a combination thereof.

DETERMINING OBJECT ORIENTATION FROM AN IMAGE WITH MACHINE LEARNING

Absstract of: US20260237177A1

Apparatuses, systems, and techniques to determine orientation of an objects in an image. In at least one embodiment, images are processed using a neural network trained to determine orientation of an object.

CONTROLLING AGENTS USING Q-TRANSFORMER NEURAL NETWORKS

Absstract of: US20260236740A1

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for controlling an agent interacting with an environment using a Transformer neural network.

AI-BASED METHOD AND SYSTEM FOR AUTOMATIC OPTIMIZATION OF DISTRIBUTED COMPUTING TASKS FOR BIG DATA

Absstract of: WO2026165976A1

The present invention relates to the technical field of AI, and provides an AI-based method and system for automatic optimization of distributed computing tasks for big data. The method comprises: constructing a multi-modal spatiotemporal feature perception network to extract spatiotemporal features of tasks and resources, and training a hierarchical hybrid decision network to perform global task scheduling and local resource allocation. A hierarchical deep reinforcement learning architecture is used for a global policy network, which combines Monte Carlo tree search and prioritized experience replay to generate decisions. A local execution network optimizes local deployment on the basis of a graph neural network and multi-agent collaborative learning. In addition, a distributed anomaly detection network is deployed to monitor performance in real time, adaptive tuning is achieved by means of reinforcement transfer learning, and finally the perception network is updated by means of knowledge distillation, thereby achieving model evolution. The present invention can effectively improve the execution efficiency and resource utilization rate of distributed computing tasks for big data, and reduce system operation costs.

DEVICE SETTINGS OPTIMIZATION

Absstract of: WO2026169963A1

A method for optimizing device settings of a plurality of devices includes receiving a performance characteristics target for devices manufactured according to a common design, wherein each device is configurable via device settings and exhibits performance variations over process variations and device operating conditions. The method includes defining a plurality of test cases, each including a combination of a respective device, a process variation, and a device operating condition. The method includes applying a first genetic adaptation algorithm to produce test results, training a neural network to generate predicted performance characteristics, and determining, by using the trained neural network as a surrogate model and applying a second genetic adaptation algorithm, a global set of device settings that collectively achieves the performance characteristics target across the plurality of devices.

RISK-BASED TRUST SCORING AND OPERATIONALIZATION FRAMEWORK FOR GENERATIVE ARTIFICIAL INTELLIGENCE MODELS

Absstract of: WO2026170170A1

A method for providing a Generative Artificial Intelligence (GenAI) system with trustworthiness evaluation, wherein the method comprises processing a training dataset that the GenAI was trained upon; constructing a plurality of latent knowledge anchors (LKAs) by applying topic modeling on the processed training dataset, wherein the plurality of LKAs comprises domain-specific knowledge representations within the processed training dataset; training a neural network classifier using the LKAs and the processed training data; evaluating, using the neural network classifier, a response generated by the GenAI to generate a trust score, wherein the trust score indicates the alignment level of the response to the training dataset and/or the comprehensiveness of the response compared to the training dataset; in response to the trust score exceeding a threshold, presenting the response to a user; and in response to the trust score not exceeding the threshold, issuing a command for the GenAI to conduct additional actions.

DIGITAL IMAGE PROCESSING FOR GENERATING MULTI-CHANNEL IMAGES

Absstract of: WO2026169910A1

Systems, apparatuses, and methods disclosed herein relate to a digital image processing system. In one aspect, the digital image processing system includes one or more processors and one or more computer-readable media storing instructions which, when executed by the one or more processors, cause the digital image processing system to access a digital image depicting a portion of a biological sample obtained from a subject. A projecting space and a staining category for an image conversion is defined by the digital image processing system, causing the digital image to be projected to the projecting space using a neural network model. The projected image is output by the digital image processing system.

QUANTUM, BIOLOGICAL, COMPUTER VISION, AND NEURAL NETWORK SYSTEMS FOR INDUSTRIAL INTERNET OF THINGS

Absstract of: AU2026208040A1

Abstract Computer-implemented method transmits a predictive model from a first device to a second device. The first device receives data values of a data stream comprising sensor data collected from one or more sensor devices in an industrial environment. Using the received data values, the first device generates and refines a first predictive model for predicting future data values, including determining and adjusting predictive model parameters based on newly received data values. The first device transmits the predictive model parameters to the second device. The second device receives the predictive model parameters and parameterizes a second predictive model using the received parameters. The second predictive model predicts future values of the first device. Based at least in part on the predicted future values, the second device causes a physical control action to be performed with respect to a physical component in the industrial environment. The predictive model parameters may be updated and retransmitted during operation. Abstract to FIG. 3 Self Organizing Network Coding to FIG. 2 Data Pool Predictive Trained Diagnostics Maintenance Models Data Rights Config. Semantic Semantic System Pool Management Automation Processing Pricing Policy Decision User Order Analysis Automation Engine Analytics Private Cloud Ad and Anticipation Location Based Customer Storage Content Targeting of State Services Applications Analytics Expert Pattern Speech Other Services Dynamic Systems

METHOD AND SYSTEM FOR ZERO-SHOT SPEAKER-ADAPTIVE SPEECH SYNTHESIS

Absstract of: US20260237377A1

0000 There is provided a method for synthesizing a speech waveform from text data. The method comprises: determining, from the text data, a phoneme sequence; obtaining a reference speech waveform comprising a high-level speech representation of a reference speaker speaking a reference speech; applying a trained neural network to the high-level speech representation to extract speaker embeddings; and determining, from the speaker embeddings and the phoneme sequence, a synthesized speech waveform indicative of the reference speaker speaking the text data.

FINGERPRINT INDEXING USING CONVOLUTIONAL NEURAL NETWORK

Absstract of: US20260236527A1

A method of filtering fingerprint candidates, the method being carried out by an indexing module arranged to access a Convolutional Neuronal Network, CNN configured to output at least one feature of an input image. The method comprises processing an image representative of local information of a searched fingerprint, by the CNN to obtain at least one feature for the searched fingerprint; retrieving a candidate fingerprint in a database; determining whether at least one feature of the retrieved candidate fingerprint matches with the at least one feature of the searched fingerprint; if the at least one feature of the retrieved candidate fingerprint matches with the at least one feature of the searched fingerprint, passing the at least one candidate fingerprint to a matching module for further comparison between the candidate fingerprint and the searched fingerprint. Other aspects are also considered.

NEURAL NETWORK-BASED IMAGE LIGHTING

Absstract of: US20260237124A1

Apparatuses, systems, and techniques are presented to generate image data. In at least one embodiment, one or more neural networks are used to cause a lighting effect to be applied to one or more objects within one or more images based, at least in part, on synthetically generated images of the one or more objects.

SYSTEMS, APPARATUSES, AND METHODS FOR MONITORING ORGAN HEALTH

Absstract of: WO2026169639A1

A system for training at least one graph neural network (GNN) for monitoring organ health includes at least one memory configured to store instructions and at least one processor configured to execute the instructions to cause the system to obtain a plurality of parameters from healthy individuals and diseased individuals, perform causal discovery to determine one or more causal relationships between the plurality of organ parameters, train the at least one GNN with the one or more causal relationships to create a trained GNN configured to output a multi-organ health status based on patient parameters. The system is also configured to train at least one acute event prediction model to predict at least one acute or adverse event for at least one organ

CAMERA-SPECIFIC EMBEDDINGS IN BIRDS-EYE-VIEW NEURAL NETWORK

Absstract of: US20260237189A1

0000 An apparatus for processing image data includes a memory for storing the image data and processing circuitry in communication with the memory. The processing circuitry is configured to obtain image data including a current set of multiple camera images from multiple cameras. According to such an example, the apparatus may also generate respective feature vectors from each of the multiple camera images with a shared image feature encoder using camera-specific positional embeddings associated with different respective cameras used to capture the multiple camera images. The apparatus may also perform a perception task using the respective feature vectors.

DEVICE FOR ACQUIRING MAGNETIC RESONANCE IMAGE ON BASIS OF DEEP LEARNING MODEL AND CONTROL METHOD THEREOF

Absstract of: EP4790443A1

The present disclosure provides an apparatus for restoring the quality of magnetic resonance images based on a deep learning model and a method of controlling the same. The method includes: obtaining a training image corresponding to each magnetic resonance image by applying at least one of a plurality of elements set in connection with the quality of the magnetic resonance image to a magnetic resonance signal corresponding to the magnetic resonance image; obtaining a training dataset including the magnetic resonance image as label data and the obtained training image as input data matching the label data; and training a neural network model based on the training dataset and context data corresponding to the training image. Obtaining the training image includes distorting the magnetic resonance signal by applying the at least one of the plurality of elements and obtaining the training image based on the distorted magnetic resonance signal.

NEURAL NETWORK TRAINING METHOD AND RELATED DEVICE

Nº publicación: EP4790604A1 12/08/2026

Applicant:

HUAWEI CLOUD COMPUTING TECH CO LTD [CN]
Huawei Cloud Computing Technologies Co., Ltd.

Absstract of: EP4790604A1

Embodiments of this application disclose a neural network training method. A first module in a federated neural network is deployed in each of a plurality of first devices. The first module includes a feature extraction module. A plurality of second modules in the federated neural network and early exit modules connected to the respective second modules are deployed in a second device. It can be learned that, in a federated learning process, the second device may include a plurality of early exit nodes, and each early exit node corresponds to one second module and a corresponding early exit module connected to the second module. In this way, after federated learning, when a target network is deployed in the first device, a structure of the target network may be in a plurality of forms based on the plurality of early exit nodes. In other words, target networks of different structures may be flexibly deployed in different first devices. For example, flexible scheduling may be performed based on resource statuses of different first devices, so that each first device can implement efficient data processing through a target network of an appropriate scale.