Ministerio de Industria, Turismo y Comercio LogoMinisterior
 

Neural networks

Resultados 112 results.
LastUpdate Updated on 19/11/2026 [12:09:00]
pdfxls
Solicitudes publicadas en los últimos 30 días / Applications published in the last 30 days
Results 1 to 25 of 112 nextPage  

POWER CROSS-MODAL BIDIRECTIONAL KNOWLEDGE TRANSFER METHOD AND APPARATUS, AND DEVICE AND STORAGE MEDIUM

Publication No.:  EP4841514A1 18/11/2026
Applicant: 
CHINA ELECTRIC POWER RESEARCH INST [CN]
STATE GRID CORP CHINA [CN]
China Electric Power Research Institute
State Grid Corporation of China
EP_4841514_A1

Absstract of: EP4841514A1

0001 The present invention relates to the technical field of knowledge transfer, and specifically to a power cross-modal bidirectional knowledge transfer method and apparatus based on intermediary space construction, and a device and a storage medium. The method comprises: using graph modeling and a graph neural network to extract a first feature of first modal data, and using a large language model to extract a second feature of second modal data; on the basis of the similarity between the first feature and the second feature and a corresponding loss function, constructing an intermediary space; using a loss function in the intermediary space to iteratively optimize parameters in the graph neural network and the large language model; and on the basis of the graph modeling, the graph neural network with parameters iteratively optimized, and the feature extracted by the large language model, performing knowledge transfer in the intermediary space. By means of the method, relationship features extracted in different modes are aligned in an intermediary space, thereby realizing bidirectional knowledge transfer between different modal data.

IMPROVED GRAPH NEURAL NETWORK MODEL FOR DENTAL THREE-DIMENSIONAL MODELS

Publication No.:  EP4839914A1 18/11/2026
Applicant: 
3SHAPE AS [DK]
3Shape A/S
EP_4586219_PA

Absstract of: EP4586219A1

A computer-implemented method for training a graph neural network (GNN) model (106) is provided. The method includes generating a graph (404, 406) corresponding to a three-dimensional (3D) mesh (302) wherein the 3D mesh (302) is associated with a surface information of at least a portion of a dental arch. Further, ground truth data indicating features of the 3D mesh (302) to be predicted by the GNN model (106) is obtained. The graph (404, 406) of the 3D mesh (302) and the ground truth data are provided, as an input, to the GNN model (106) wherein the GNN model (106) comprises a set of convolution layers. Furthermore, a set of weights is applied to each convolution layer of the set of convolution layers, wherein the set of weights corresponds to differences between features of nodes of the graph (404, 406). The method further comprises receiving, as an output of the GNN model (106) with the applied set of weights, output data indicating predicted features of the 3D mesh (302). The method additionally comprises iteratively updating trainable parameters of the GNN model (106) based on comparing the output data to the ground truth data until a predefined loss function threshold is reached.

NEURAL NETWORK TUNING USING TEXT ENCODER

Publication No.:  EP4839878A1 18/11/2026
Applicant: 
SNAP INC [US]
SNAP, INC.
WO_2025151365_PA

Absstract of: WO2025151365A1

Methods, systems, and non-transitory computer-readable mediums for tuning a generative text-to-image neural network. Text prompts are processed using a pre-trained text encoder to obtain embedded text prompts, which are used by a pre-trained diffusion model to generate images. Reward scores are iteratively determined for the images while the pre-trained diffusion model is fixed and weights of the pre-trained text encoder are updated to fine tune the neural network in order to improve the quality of generated images. Additionally, reward scores for the images can then be determined with the updated weights of the text encoder fixed to update weights of the pre-trained diffusion model to further fine tune the neural network.

SYSTEM AND METHOD OF INTELLIGENT VEGETATION MANAGEMENT

Publication No.:  EP4841586A2 18/11/2026
Applicant: 
AIDASH INC [US]
Aidash Inc.
EP_4841586_PA

Absstract of: EP4841586A2

0001 A method comprising receiving a first set of aerial images of a geographic area, receiving locations of assets, determining a likely location of at least one asset within each image, creating one or more bounding boxes, encompassing the likely location of one or more assets within each of the images, providing any number of the images to a convolutional neural network to classify pixels, the classification of each of the pixels indicating if the pixels are part of one or more obstructions or are part of a different classification, determining at least one zone, the zone encompassing the at least one asset, determining a distance between at least one pixel part of an obstruction and the zone, generating a criticality score based on the distance, comparing the criticality score to a threshold, and providing an alert of a future hazardous condition based on the criticality score.

OBJECT CLASSIFICATION

Publication No.:  EP4841581A1 18/11/2026
Applicant: 
BAE SYSTEMS PLC [GB]
BAE SYSTEMS plc
EP_4841581_PA

Absstract of: EP4841581A1

There is described a computer implemented method of training a neural network for object classification. The method comprises inputting a set of training images comprising objects to be classified into the neural network, wherein the network is configured to perform feature extraction on the set of training images, and learn a set of prototypes (14) based on the feature extraction, and learn gradients for prototype activation of the set of protypes based on inverse attention weighting.

DEEP LEARNING BASED SYSTEMS AND METHODS FOR DISEASE RISK PHENOTYPING

Publication No.:  WO2026236642A1 12/11/2026
Applicant: 
MYOME INC [US]
MYOME, INC.
WO_2026236642_A1

Absstract of: WO2026236642A1

A method for determining whether a subject is at increased risk for a disease may include generating an integrated risk score (IRS) for a subject, wherein the IRS indicates a risk of a particular disease or disease group for the subject, and wherein generating the IRS includes (1) extracting, by one or more first neural network models, values of a plurality of features from health data of the subject, and (2) classifying, by one or more second models and based on the values of the plurality of features, the risk of the particular disease or disease group for the subject; determining one or more recommended actions for the subject based at least in part on the IRS; and providing an indication of the one or more recommended actions for the subject.

MULTICORE-BASED DEEP LEARNING ACCELERATOR AND METHOD FOR OPTIMIZING CORE THEREOF

Publication No.:  US20260359620A1 12/11/2026
Applicant: 
HYUNDAI MOTOR CO [KR]
KIA CORP [KR]
Hyundai Motor Company
Kia Corporation

Absstract of: US20260359620A1

A multicore-based deep learning accelerator includes a neural processing unit including a plurality of cores configured to enable parallel processing of a neural network model and a storage unit storing a first binary configured to cause the plurality of cores to perform inference based on the neural network model and a second binary configured to cause the remaining cores, excluding a portion of the plurality of cores, to perform inference based on the neural network model, wherein the neural processing unit is configured to perform inference based on the neural network model using a core combination configured based on a binary selected from the first binary and the second binary.

PRODUCT PRODUCTION QUALITY INSPECTION MANAGEMENT METHOD AND SYSTEM BASED ON QUANTUM SENSING

Publication No.:  WO2026232905A1 12/11/2026
Applicant: 
ZHEJIANG YUEXIN TECH CO LTD [CN]
\u6D59\u6C5F\u8D8A\u65B0\u79D1\u6280\u80A1\u4EFD\u6709\u9650\u516C\u53F8
WO_2026232905_A1

Absstract of: WO2026232905A1

The present invention relates to the technical field of industrial automation and quantum detection. Provided are a product production quality inspection management method and system based on quantum sensing. The method comprises: collecting a quantum phase difference, a spin relaxation time, and energy density data of a product by means of a quantum sensing array; performing quantum-state decoupling processing on multi-dimensional field data, and extracting a quantum chromatic homogeneity coefficient and a structural anomaly index; constructing a multi-scale convolutional neural network to generate a three-dimensional quality feature tensor; on the basis of a quantum annealing algorithm, dynamically optimizing a defect determination threshold value; and generating a visualized heat map, and triggering a process control instruction. The system includes a quantum sensing module, an edge computing unit, a dynamic decision engine, a human-machine interaction terminal and a feedback control module, and implements closed-loop management by means of synchronous multiphysics collection and real-time control. The present invention uses quantum sensing to overcome the resolution limitations of conventional detection, so as to accurately identify microscopic defects, and adapts to complex operation conditions by means of dynamic threshold value optimization.

DISTRIBUTED PLACEMENT OF LINEAR OPERATORS FOR ACCELERATED DEEP LEARNING

Publication No.:  US20260359145A1 12/11/2026
Applicant: 
CEREBRAS SYSTEMS INC [US]
Cerebras Systems Inc.
WO_2021084485_A1

Absstract of: US20260359145A1

Techniques in distributed placement of linear operators for accelerated deep learning provide improvements in one or more of accuracy, performance, and energy efficiency. An array of processing elements comprising a portion of a neural network accelerator performs flow-based computations on wavelets of data. Each processing element comprises a compute element to execute programmed instructions using the data and a router to route the wavelets. The routing is in accordance with virtual channel specifiers of the wavelets and controlled by routing configuration information of the router. A software stack determines distributed placement of linear operators based on a description of a neural network. The determined placement is used to configure the routers including usage of the respective colors. The determined placement is used to configure the compute elements including the respective programmed instructions each is configured to execute.

NEURAL NETWORK MODEL AND LEARNING METHOD OF THE SAME

Publication No.:  US20260359603A1 12/11/2026
Applicant: 
SEMICONDUCTOR ENERGY LABORATORY CO LTD [JP]
Semiconductor Energy Laboratory Co., Ltd.
WO_2021130594_A1

Absstract of: US20260359603A1

A neural network model that can perform highly accurate processing on input data is provided. The neural network model includes first and second neutral networks, and the first neural network includes a first layer, a second layer, and a third layer. A feature map output from the first layer is input to the second layer and the second neural network, and a feature map output from the second neural network is input to the third layer. Given that the feature map output from the first layer when first data is input to the first neural network is a correct feature map and that the feature map output from the first layer when second data obtained by adding noise to the first data is input to the first neural network is a learning feature map, the second neural network is learned so that a feature map output from the second neural network matches the correct feature map when the learning feature map is input.

IMAGE-PROCESSING-ALGORITHM-BASED METHOD AND SYSTEM FOR UNMANNED AERIAL VEHICLES TO IMPLEMENT INTELLIGENT INTEGRATED INSPECTION FOR POWER TRANSMISSION, POWER TRANSFORMATION AND POWER DISTRIBUTION, AND MEDIUM

Publication No.:  WO2026232751A1 12/11/2026
Applicant: 
STATE GRID SICHUAN YAAN ELECTRIC POWER GROUP CO LTD [CN]
\u56FD\u7F51\u56DB\u5DDD\u96C5\u5B89\u7535\u529B\uFF08\u96C6\u56E2\uFF09\u80A1\u4EFD\u6709\u9650\u516C\u53F8
WO_2026232751_A1

Absstract of: WO2026232751A1

Disclosed in the present invention are an image-processing-algorithm-based method and system for unmanned aerial vehicles to implement power transmission, power transformation and power distribution, and a medium. The method comprises: constructing a gridded intelligent inspection network, and providing drone docks each integrating charging, meteorological monitoring and 5G communication; a central control platform integrating inspection requirements for power transmission, power transformation and power distribution, and dynamically optimizing task sequences; unmanned aerial vehicles acquiring device images, and generating optimized images by means of multi-dimensional feature fusion; determining an optimal segmentation threshold value by using an improved MFB-Otsu algorithm and in combination with Gaussian process modeling; using a multi-scale deep convolutional neural network and a cross-domain attention mechanism to implement intelligent defect recognition, and outputting a three-dimensional evaluation result including type, position and severity; and realizing real-time edge processing and closed-loop optimization of the central platform by means of a two-level architecture. The present invention realizes efficient and collaborative inspection of the power transmission devices, power transformation devices and power distribution devices, improves the accuracy and efficiency of defect recognition, and has the characteristics of realizing adaptive optimization and cross-do

SYSTEMS AND METHODS FOR COMPUTING FEATURING SYNTHETIC COMPUTING OPERATORS AND COLLABORATION

Publication No.:  AU2025261949A1 12/11/2026
Applicant: 
SUN & THUNDER LLC [US]
SUN & THUNDER, LLC
AU_2025261949_PA

Absstract of: AU2025261949A1

One embodiment is directed to a synthetic engagement system for process-based problem solving, comprising: a computing system comprising one or more operatively coupled computing resources; and a user interface operated by the computing system and configured to engage a human operator in accordance with a predetermined process configuration toward an established requirement based at least in part upon one or more specific facts; wherein the user interface is configured to allow the human operator to select and interactively engage one or more synthetic operators operated by the computing system to proceed through the predetermined process configuration, and to return result to the human operator selected to at least partially satisfy the established requirement; and wherein each of the one or more synthetic operators is informed by a convolutional neural network informed at least in part by historical actions of a particular actual human operator and a synthetic operator background configuration.

METHODS AND SYSTEMS FOR WORD EDIT DISTANCE EMBEDDING

Publication No.:  US20260360355A1 12/11/2026
Applicant: 
COLLIBRA BELGIUM BV [BE]
Collibra Belgium BV
WO_2021205221_A1

Absstract of: US20260360355A1

A system for classifying words in a batch of words can include at least one memory device storing instructions for causing at least one processor to create dictionary vectors for each of a plurality of dictionary words using a neural network (NN), store each dictionary vector along with a classification indicator corresponding to the associated dictionary word, and create word vectors for each word in a batch of words for classification using the NN. The closest matching dictionary vectors are found for each word vector and the classification indicators of the closest matching dictionary vector for each word vector in the batch is reported.

CONTENT-AWARE STYLE ENCODING USING NEURAL NETWORKS

Publication No.:  US20260360037A1 12/11/2026
Applicant: 
NVIDIA CORP [US]
NVIDIA Corporation
GB_2596901_PA

Absstract of: US20260360037A1

Apparatuses, systems, and techniques to facilitate application of a style, for which one or more neural networks have not been trained by a training framework, from one image to content of another image. In at least one embodiment, a styled output image is generated by one or more neural networks based on a style contained in a style image and content of a content image where said one or more neural networks have not been trained by a training framework on said style.

CHANNELWISE FEATURE REORIENTATION AND MERGING WITH NEIGHBOURING FEATURES FOR ROBUST LOW COMPLEXITY DNN BASED AUDIO PROCESSING

Publication No.:  AU2025266039A1 12/11/2026
Applicant: 
FRAUNHOFER GES ZUR FOERDERUNG DER ANGEWANDTEN FORSCHUNG E V [DE]
FRAUNHOFER-GESELLSCHAFT ZUR F\u00D6RDERUNG DER ANGEWANDTEN FORSCHUNG E.V.
AU_2025266039_PA

Absstract of: AU2025266039A1

There is disclosed an apparatus (10) for processing an input information signal (20), comprising: * a feature extractor (100) for extracting a set of features (102) from the input information signal (20), the set of features (102) having a first shape, * a feature block generator (200, CR1) configured to reshape the set of features (102) from a first shape to a second shape by: - segmenting (210) the set of features (102) into at least 3 feature subsets (212, 212a-212h), each feature subset (212, 212a-212h) having a specific shape, - performing a subsampling (220, 220a, 220b) of the feature subsets (212) to generate a plurality of feature blocks (222, 222a-222d) by stacking a selected set of the subsampled feature subsets feature subsets (212, 212a-212h) along a first dimension, - creating (230) a feature hyper-block (332) of the second shape by stacking the plurality of feature blocks (222, 222a-222d) along a second dimension, * a neural network processor (300, D1 ) configured to process the feature hyper block (332) to obtain a first result (380); and * an output post-processor (P2, 700) configured to post-process the result (380) to construct an output information signal (40) and/or to output a classification result.

LIGHT ESTIMATION USING NEURAL NETWORKS

Publication No.:  US20260360076A1 12/11/2026
Applicant: 
SNAP INC [US]
Snap Inc.
WO_2022146841_A1

Absstract of: US20260360076A1

A messaging system performs image processing to estimate lighting properties with neural networks for images provided by users of the messaging system. A method of estimating light properties includes receiving an input image with first lighting properties and processing the input image using a convolutional neural network to generate an estimate of the first lighting properties. The method may further include modifying the input image with an augmentation to generate a modified input image, where the augmentation has second lighting properties, and changing the second lighting properties of the augmentation in the modified input image to the estimate of the first lighting properties.

Low-Rank Adaptation of Neural Network Models

Publication No.:  US20260359642A1 12/11/2026
Applicant: 
MICROSOFT TECH LICENSING LLC [US]
Microsoft Technology Licensing, LLC
WO_2022245502_PA

Absstract of: US20260359642A1

A computer implemented method obtains neural network-based model base model weight matrices for each of multiple neural network layers. First low-rank factorization matrices are added to corresponding base model weight matrices to form a first domain model. The low-rank factorization matrices are treated as trainable parameters. The first domain model is trained with first domain specific training data without modifying base model weight matrices.

SCANNING ELECTRON MICROSCOPE IMAGE PROCESSING USING NEURAL NETWORK

Publication No.:  US20260360103A1 12/11/2026
Applicant: 
SAMSUNG ELECTRONICS CO LTD [KR]
Samsung Electronics Co., Ltd.
US_20240071033_PA

Absstract of: US20260360103A1

A neural network device includes: (1) a pre-processor configured to select target images from scanning electron microscope (SEM) images, based on frequencies respectively corresponding to the SEM images, and crop each of the target images into a plurality of cropped images; (2) a neural network processor configured to generate a crop detection image by inferring a target object from each of the plurality of cropped images by using a segmentation model trained to detect the target object in each of the plurality of cropped images; and (3) a post-processor configured to merge crop detection images with each other in a same size as the SEM images, based on position information of the plurality of cropped images.

MULTI-TASKING ACTION UNIT PREDICTIONS

Publication No.:  US20260360183A1 12/11/2026
Applicant: 
HEWLETT PACKARD DEVELOPMENT CO L P [US]
PURDUE RES FOUNDATION [US]
Hewlett-Packard Development Company, L.P.
Purdue Research Foundation
WO_2024085875_PA

Absstract of: US20260360183A1

In an example in accordance with the present disclosure, a multi-tasking learning expression tracking system is described. The system includes a feature extractor to extract a feature representation from an image of a user. The system also includes a classification branch having a classification neural network and the feature extractor to, during training, predict expression classes for training images having different expressions. The system also includes a regression branch comprising a regression neural network and the feature extractor to, during training, predict action unit (AU) intensities for the training images and during deployment predict an AU intensity for the image of the user.

METHOD AND APPARATUS FOR INTELLIGENT DATA PLANE BASED ON NEURAL NETWORK

Publication No.:  US20260359599A1 12/11/2026
Applicant: 
TSINGHUA UNIV [CN]
TSINGHUA UNIVERSITY
CN_118282875_PA

Absstract of: US20260359599A1

A method for an intelligent data plane based on a neural network, includes obtaining a switch classification result by deploying a recurrent neural network on a P4 programmable switch to perform line-speed analysis on traffic; forwarding a first part of traffic to a server for upgraded analysis based on the switch classification result and a classification confidence; and performing the upgraded analysis on the first part of traffic by deploying a Transformer-based model on the server.

SENSOR FUSION

Publication No.:  US20260360137A1 12/11/2026
Applicant: 
SAJJAN NEERAJ [US]
KOCAMAZ MEHMET K [US]
Sajjan Neeraj
Kocamaz Mehmet K.
DE_102024112782_PA

Absstract of: US20260360137A1

In various examples, sensor fusion for autonomous or semi-autonomous systems and applications is described. Systems and methods are disclosed that use data pipelines to process sensor data generated using different types of sensors (e.g., image sensors, RADAR sensors, LiDAR sensors, etc.) in order to generate first data representing information associated with objects surrounding a vehicle. For instance, the information may represent values for parameters associated with the objects, such as locations of the objects, dimensions of the objects, velocities of the objects, orientations of the objects, classifications of the objects, and/or any of parameters. The systems and methods may then process the first data using one or more machine learning models (e.g., one or more deep neural networks) that are trained to fuse the information (e.g., the parameters) and output second data representing final information associated with the objects. The fused output may then be used to perform downstream operations.

Detection System for Alzheimer's Disease Using Brain Structural and/or Functional Magnetic Resonance Image Processing and Machine Learning Techniques

Publication No.:  US20260360542A1 12/11/2026
Applicant: 
COUNCIL OF SCIENT & INDUSTRIAL RESEARCH [IN]
Council of Scientific & Industrial Research
WO_2024252413_A1

Absstract of: US20260360542A1

Early and accurate identification of dementia, such as Alzheimer's disease (AD) is of utmost importance. However, despite several decades of biomarker research, there is still no single diagnostic test or biomarker to definitively diagnose dementia and its underlying neurodegenerative disorder. A combination of structural MRI (fMRI) and functional MRI (fMRI) derived image analysis may provide the unique ability to capture the dynamic state of change in the degenerating brain. Hence, to capture the overall structural and functional anomalies of brain tissues caused by AD, an exhaustive combinatorial system has been developed using structural and/or functional MRI data followed by rigorous image processing and deep learning-based algorithms to diagnose AD and/or mild cognitive impairment (MCI) patients. Whole brain sMRI and fMRI slices are processed, and brain pixel-based intensity features are fed into a deep learning-based convoluted neural network (CNN) algorithm to calculate the AD/healthy probability of each MRI slice.

METHOD FOR ASSIGNING A SEMANTIC CONCEPT TO A PREVIOUSLY UNSEEN DATA ASSET

Publication No.:  EP4838381A1 11/11/2026
Applicant: 
BOSCH GMBH ROBERT [DE]
Robert Bosch GmbH
EP_4838381_PA

Absstract of: EP4838381A1

0001 A computer-implemented method assigns a semantic concept to a new data asset by: enriching (1) the data assets metadata I (tokenizing labels (A1), expanding acronyms (A2), leveraging (A3) a knowledge graph (11)/databases (14), generating descriptions (A4)); retrieving (2) candidate concepts and similarity scores via, e.g., vector database (13) searches comparing enriched metadata embeddings with concept descriptor embeddings; determining (3) a first ranking based on similarity scores; determining (4) at least a second ranking using a neural network (12b) processing the first ranking and enriched metadata; and storing a proposed mapping (O) based on at least the second ranking in a knowledge graph (11).

A METHOD AND APPARATUS FOR ENCODING OR DECODING A PICTURE USING A NEURAL NETWORK

Publication No.:  EP4838416A2 11/11/2026
Applicant: 
HUAWEI TECH CO LTD [CN]
Huawei Technologies Co., Ltd.
EP_4838416_PA

Absstract of: EP4838416A2

0001 Disclosed herein are methods and systems for encoding a picture and decoding a bitstream that may represent an encoded picture. During encoding and decoding, rescaling operations are applied to rescale an input to a size that can be processed by a layer of a neural network. Embodiments disclosed herein provide methods for rescaling that achieve a reduced size of the bitstream, thereby improving compression.

COMPILATION METHOD AND APPARATUS FOR NEURAL NETWORK MODEL, INFERENCE METHOD AND APPARATUS FOR NEURAL NETWORK MODEL, AND DEVICE AND MEDIUM

Nº publicación: US20260350344A1 05/11/2026

Applicant:

BEIJING HORIZON INFORMATION TECH CO LTD [CN]
Beijing Horizon Information Technology Co., Ltd.

US_20260350344_A1

Absstract of: US20260350344A1

Disclosed are a compilation and inference method for a neural network model, and a device and a medium. The compilation method comprises: acquiring a first model corresponding to a neural network model to be subjected to compilation; using, as a target network layer, any one of at least one network layer which includes a preset operation in the first model, and converting the preset operation of the target network layer into a convolution operation which is supported by a neural network processor, so as to obtain a converted first network layer, wherein the preset operation is an operation comprising a multiply—accumulate operation; on the basis of the converted first network layer, obtaining an optimization model corresponding to the first model; and according to the optimization model, generating a target instruction sequence that is executable by the neural network processor and corresponds to said neural network model.

traducir