Neural networks

INFERENCE-AWARE FINE-TUNING OF GENERATIVE NEURAL NETWORKS

Absstract of: WO2026075993A1

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for training a generative neural network using an inference-aware fine-tuning framework to mitigate the difference between how the generative neural network has been trained and how the generative neural network will be used at inference time.

A SHALE FRACTURE SEISMIC IDENTIFICATION METHOD BASED ON 3D U-NETCONVOLUTIONAL NEURAL NETWORK COMBINED WITH ANT TRACKING

Absstract of: WO2026073521A1

A shale fracture seismic identification method based on a 3D U-Net convolutional neural network combined with ant tracking is disclosed. The method establishes a geological model of shale fractures using single-well data and performs seismic forward modeling to determine the advantageous frequency band for fracture identification. Spectral-peak decomposition is applied to obtain the advantageous frequency-band data volume, which is processed using a 3D U-Net convolutional neural network and ant-tracking computation to generate a 3D U-Net Ant Tracking volume. The results are verified using microseismic data, and along-layer attributes of the 3D U-Net Ant Tracking volume are extracted to determine the regional planar distribution characteristics of shale fractures. The method effectively reduces exploration costs by combining single-well and seismic data, significantly improves seismic resolution through integrated application of seismic forward modeling, spectral-peak decomposition, and advantageous frequency-band data computation, and expands the range of fracture identification by extracting along-layer slices from the data volume.

METHODS OF PROVIDING DATA PRIVACY FOR NEURAL NETWORK BASED INFERENCE

Absstract of: EP4722968A2

Methods and systems that provide data privacy for implementing a neural network-based inference are described. A method includes injecting stochasticity into the data to produce perturbed data, wherein the injected stochasticity satisfies an ε-differential privacy criterion and transmitting the perturbed data to a neural network or to a partition of the neural network for inference.

ELECTRONIC NOSE INSTRUMENT OPERABLE IN BOTH SCHEDULED AND ON-DEMAND MODES AND METHOD FOR ONLINE REAL-TIME DETECTION AND ANALYSIS OF MULTI-COMPONENT ODORS

Absstract of: WO2026065613A1

An electronic nose instrument operable in both scheduled and on-demand modes and a method for online real-time detection and analysis of multi-component odors. A hardware unit of the electronic nose instrument mainly comprises: a gas-sensitive sensor array module (I), a headspace sampling module (II), a pressurization cylinder (III), a computer control and analysis module (IV), a backup power supply (V), and a clean air cylinder (VI). A main housing integrates the first four components. Within a cycle time T=180-600 s, the pressurization cylinder (III) significantly increases a gas-sensitive response by means of short-term pressure multiplication. The gas-sensitive sensor array obtains a 50-dimensional sensing sample for single detection. A large odor dataset X comprises online detection data from the electronic nose instrument, and offline detection data from olfactometry and chromatography etc. The detection data is decomposed into multiple single-concentration sub-tasks. A machine learning cascade model is formed by multiple learning groups consisting of single neurons, and shallow and deep neural networks. The electronic nose instrument can flexibly achieve online real-time identification of odor pollutants and multi-component concentration estimation and prediction.

FEATURE FUSION CLASSIFICATION METHOD FOR MULTIPLE TYPES OF PACKAGING BAG

Absstract of: WO2026064957A1

Disclosed is a feature fusion classification method for multiple types of packaging bag, relating to the technical field of classification of multiple types of packaging bag. On the basis of a random forest concept, the present invention provides a feature fusion classification algorithm for multiple types of packaging bag. By means of three different classification methods: a support vector machine, template matching, and a neural network, denoising processing is performed on images of various packaging bags transmitted from a camera using a median filter, and on the basis of a homomorphic filtering algorithm, enhancement processing is performed on the denoised images. The images are classified by separately using a support vector machine model, a template matching algorithm, and a neural network model, and a majority rule-based voting mechanism is implemented for prediction results of the three methods, to obtain a final result. The voting mechanism-based feature fusion classification algorithm for multiple types of packaging bag of the present invention provides high accuracy, reduces error generation, and obtains more accurate results.

POLY-SCALE KERNEL-WISE CONVOLUTION FOR HIGH-PERFORMANCE VISUAL RECOGNITION APPLICATIONS

Absstract of: US20260094429A1

Techniques related to poly-scale kernel-wise convolutional neural network layers are discussed. A poly-scale kernel-wise convolutional neural network layer is applied to an input volume to generate an output volume and include filters each having a number of filter kernels with the same sample rate and differing dilation rates optionally in a repeating pattern of dilation rate groups within each of filters with the pattern of dilation rate groups offset between the filters the poly-scale kernel-wise convolutional neural network layer.

METHOD FOR PREDICTING PRICE OF CRYPTOCURRENCY ON BASIS OF ARTIFICIAL NEURAL NETWORK

Absstract of: WO2026071683A1

According to an embodiment of the present disclosure, disclosed is a method for predicting the price of cryptocurrency on the basis of an artificial neural network. The method may comprise the steps of: acquiring monitoring reference information from a user terminal; generating a chart image according to the monitoring reference information; generating a pattern prediction result corresponding to the chart image on the basis of an artificial neural network-based pattern prediction model; and transmitting, to the user terminal, notification information generated on the basis of the pattern prediction result.

NEIGHBORING BOUNDING BOX AGGREGATION FOR NEURAL NETWORKS

Absstract of: US20260094399A1

0000 Apparatuses, systems, and techniques to generate bounding box information. In at least one embodiment, for example, bounding box information is generated based, at least in part, on a plurality of candidate bounding box information.

VEHICLE CONTROL DEVICE AND METHOD FOR CONTROLLING VEHICLE

Absstract of: WO2026070140A1

The present disclosure relates to vehicle control based on a neural network. In particular, the present disclosure relates to determining confidence in the output of a neural network by comparing a firing pattern observed during operation of a vehicle with a reference firing pattern obtained by observing firing of neurons during a training phase.

METHOD AND DEVICE FOR ENHANCED IMAGE PROCESSING USING VISION GRAPH NEURAL NETWORK

Absstract of: WO2026069149A1

It is described a method for processing an image using a vision graph neural network, said vision graph neural network comprising a window-based grapher module (7) including a first fully connected layer with batch normalization (9), a windows partitioning module (10), a dynamic graph convolution module (11), a windows reverse module (12), a second fully connected layer with batch normalization (13) and a skip connection (15), wherein said window-based grapher module (7) is configured to: - process a feature vector (X) of said image (2) through said first fully connected layer with batch normalization (9) to obtain a normalized feature vector; - partition said normalized feature vector into a plurality of non-overlapping windows using said windows partitioning module (10); - for each window, construct a graph where nodes represent patches of said image (2) within the respective window and edges represent relationships between said nodes, and apply a graph convolutional operation to each graph to update node features within each window using said dynamic graph convolution module (11); - reshape the updated node features from each window back into the format of said normalized feature vector using said windows reverse module (12); - process the reshaped feature vector through said second fully connected layer with batch normalization (13); combine said feature vector (X) directly with an output of said second fully connected layer with batch normalization (13) using said skip c

INFORMATION PROCESSING DEVICE, INFORMATION PROCESSING METHOD, AND PROGRAM

Absstract of: WO2026069497A1

This information processing device performs predetermined processing using a neural network model and comprises an inference unit that performs the predetermined processing using the model. The model includes a positional encoding unit that calculates relative positional information of each token in a token string using a wavelet function, and an attention mechanism that calculates a latent representation of the token string using the positional information.

METHOD FOR CONSTRUCTING GAN-BASED DEFECT DETECTION MODEL FOR POLE PIECES OF BLADE BATTERY

Absstract of: WO2026066156A1

Disclosed in the present invention is a method for constructing a GAN-based defect detection model for pole pieces of a blade battery. The method comprises the following steps: collecting several images of defective target pole pieces; pre-processing the images to obtain pre-processed images, and extracting valid defective regions from the images; acquiring contour information for the valid regions, and accurately classifying the contour information on the basis of characteristic parameters; performing data augmentation on classified data, so as to obtain an augmented dataset; and in the dataset, using defect types and position information as labels to train a neural network, and using a neural network model as a defect detection model for pole pieces of a blade battery. In the present invention, a dataset that has undergone data augmentation is inputted into a network as a training set, such that the problem of a severe shortage of training samples caused by numerous types of battery pole piece defects and low occurrence probabilities of individual samples is solved, and the detection accuracy of a defect detection model for pole pieces of a battery is greatly improved, thereby enabling the rapid and accurate detection of various defects and position information of pole pieces of a blade battery.

INFORMATION PROCESSING METHOD AND INFORMATION PROCESSING DEVICE

Absstract of: WO2026070418A1

In this information processing method using a neural network for a structure represented as a set of nodes arranged in space, a computer executes processing including: receiving input of a state of each node; calculating, on the basis of states between the nodes, a frame representing a coordinate axis for each node; and extracting, using the frame, information having predetermined symmetry of the structure from each node.

NEURAL NETWORK QUANTIZATION PARAMETER DETERMINATION METHOD AND RELATED PRODUCTS

Absstract of: EP4718326A2

0001 The technical solution involves a board card including a storage component, an interface apparatus, a control component, and an artificial intelligence chip. The artificial intelligence chip is connected to the storage component, the control component, and the interface apparatus, respectively; the storage component is used to store data; the interface apparatus is used to implement data transfer between the artificial intelligence chip and an external device; and the control component is used to monitor a state of the artificial intelligence chip. The board card is used to perform an artificial intelligence operation.

ELECTRONIC DEVICE FOR EXECUTING NEURAL NETWORK MODEL INCLUDING NON-LINEAR OPERATION AND OPERATION METHOD THEREOF

Absstract of: EP4718327A1

0001 An electronic device for executing a neural network model including a non-linear operation and an operation method thereof are provided. The operation method of the electronic device includes obtaining data to be inferred and obtaining an inference result of the data output from the neural network model as the data is input to the neural network model including a plurality of nodes, wherein, in an inference process, a first weight applied when a value of a first node among the plurality of nodes is transmitted to a second node may be updated based on a value of a first reference node, which is any one of the plurality of nodes.

TRAINING A NEURAL NETWORK USING A DATA SET WITH LABELS OF MULTIPLE GRANULARITIES

Absstract of: EP1000000A1

The invention relates to an apparatus (1) for manufacturing green bricks from clay for the brick manufacturing industry, comprising a circulating conveyor (3) carrying mould containers combined to mould container parts (4), a reservoir (5) for clay arranged above the mould containers, means for carrying clay out of the reservoir (5) into the mould containers, means (9) for pressing and trimming clay in the mould containers, means (11) for supplying and placing take-off plates for the green bricks (13) and means for discharging green bricks released from the mould containers, characterized in that the apparatus further comprises means (22) for moving the mould container parts (4) filled with green bricks such that a protruding edge is formed on at least one side of the green bricks.

Method And Device For Monitoring Port And Ship In Consideration Of Sea Level

Absstract of: US20260087822A1

The present invention relates to a method for monitoring a harbor performed by a computing device, the method for monitoring the harbor according to an aspect of the present invention comprising: obtaining a harbor image having a first view attribute; generating a segmentation image having the first view attribute and corresponding to the harbor image by performing an image segmentation using an artificial neural network trained to output information, from an input image, related to an object included in the input image; generating a transformed segmentation image having a second view attribute from the segmentation image having the first view attribute based on a first view transformation information used to transform an image having the first view attribute into an image having the second view attribute different from the first view attribute; and calculating berthing guide information of the ship based on the transformed segmentation image.

MEDIA ENGAGEMENT THROUGH DEEP LEARNING

Absstract of: US20260088021A1

Apparatuses, systems, and techniques to facilitate understanding of media content using neural networks to adjust playback speed and volume based on environmental and other factors. In at least one embodiment, playback of media content is slowed down or sped up if audio associated with said media content is difficult to understand based on background noise, accent, difficulty of material, as well as other factors that decrease understandability of media content.

IMAGE COMPRESSION AND DECODING, VIDEO COMPRESSION AND DECODING: METHODS AND SYSTEMS

Absstract of: US20260089329A1

A computer-implemented method for lossy image or video compression, transmission and decoding, the method including the steps of (i) receiving an input image at a first computer system; (ii) encoding the input image using a first trained neural network, using the first computer system, to produce a latent representation; (iii) quantizing the latent representation using the first computer system to produce a quantized latent; (iv) entropy encoding the quantized latent into a bitstream, using the first computer system; (v) transmitting the bitstream to a second computer system; (vi) the second computer system entropy decoding the bitstream to produce the quantized latent; (vii) the second computer system using a second trained neural network to produce an output image from the quantized latent, wherein the output image is an approximation of the input image.

OBJECT IDENTIFICATIONS IN IMAGES OR VIDEOS

Absstract of: US20260087646A1

0000 An apparatus is provided. The apparatus includes a communications interface to receive raw data from an external source. The raw data includes a representation of a first object and a second object. The apparatus further includes a memory storage unit to store the raw data. In addition, the apparatus includes a neural network engine to receive the raw data. The neural network engine is to generate a segmentation map and a boundary map. The apparatus also includes a post-processing engine to identify the first object and the second object based on the segmentation map and the boundary map.

CONTROLLING A FUNCTION VIA GAZE DETECTION

Absstract of: US20260086636A1

0000 Aspects of the present disclosure relate to systems and methods for controlling a function of a computing system using gaze detection. In examples, one or more images of a user are received and gaze information may be determined from the received one or more images. Non-gaze information may be received when the gaze information is determined to satisfy a condition. Accordingly, a function may be enabled based on the received non-gaze information. In examples, the gaze information may be determined by extracting a plurality of features from the received one or more images, providing the plurality of features to a neural network, and determining, utilizing the neural network, a location at a display device at which a gaze of the user is directed.

DEEP NEURAL NETWORKS (DNN) INFERENCE USING PRACTICAL EARLY EXIT NETWORKS

Absstract of: US20260086912A1

The present disclosure relates to methods and systems for providing inferences using machine learning systems. The methods and systems receive a load forecast for processing requests by a machine learning model and split the machine learning model into a plurality machine learning model portions based on the load forecast. The methods and systems determine a batch size for the requests for the machine learning model portions. The methods and systems use one or more available resources to execute the plurality of machine learning model portions to process the requests and generate inferences for the requests.

VIRTUAL IMPACTOR-BASED LABEL-FREE PARTICULATE MATTER DETECTION USING HOLOGRAPHY AND DEEP LEARNING

Absstract of: US20260086013A1

A particulate matter detection device takes holographic images of flowing particulate matter concentrated by a virtual impactor, which selectively slows down and guides larger particles to fly through an imaging window. The flowing particles are illuminated by a pulsed laser diode, casting their inline holograms on a CMOS image sensor in a lens-free mobile imaging device. The illumination contains three short pulses with a negligible shift of the flowing particle within one pulse and triplicate holograms of the same particle are recorded at a single frame revealing different perspectives of each particle. A deep neural network classifies the particles based on the acquired holographic images. The device was tested using different types of pollen and achieved a blind classification accuracy of 92.91%. This mobile and cost-effective device weighs ˜700 g and can be used for label-free sensing and quantification of various bio-aerosols over extended periods.

IMPROVED WELLBORE CONTROL AND MODELS USING IMAGE DATA SYSTEMS AND METHODS

Absstract of: US20260085602A1

Computer implemented methods and systems for testing one or more operational changes in a drill rig includes initiating the one or more operational changes and using, in part, image data of a mechanical mud separation machines (“MMSM”) to detect the impact of the one or more changes. The image data may be processed by a Deep Neural Network to identify objects in the object flow, operational parameters of the MMSM, and wellbore environmental conditions. Additional image data may be selected for additional processing based on the results of the analysis. The results of the test may be used to update the drilling operation or a drilling model.

METHOD AND SYSTEM FOR CONTROLLING AND DISTRIBUTING WAVE ENERGY IN OFFSHORE AQUACULTURE

Nº publicación: US20260086522A1 26/03/2026

Applicant:

UNIV GUANGDONG OCEAN [CN]

Absstract of: US20260086522A1

0000 Disclosed in the present disclosure is a method and system for controlling and distributing wave energy in offshore aquaculture. The method includes: obtaining an aquaculture cycle of each aquaculture sub-zone of an offshore aquaculture zone, sorting remaining aquaculture cycles of the aquaculture sub-zones from small to large, and obtaining a plurality of work cycles according to sorting results; obtaining a predicted wave energy yield of a next work cycle through a preset neural network model; obtaining an importance coefficient value sorting result of each aquaculture zone through a preset recursive feature elimination (RFE) model; and adjusting operation cycles and operation power of first-type aquaculture apparatuses, second-type aquaculture apparatuses, and third-type aquaculture apparatuses in sequence according to an apparatus type of each aquaculture apparatus, the aquaculture zone where each aquaculture apparatus is located, the predicted wave energy yield, and the importance coefficient value sorting results.