Neural networks

SENSOR-PROCESSING SYSTEMS INCLUDING NEUROMORPHIC INTEGRATED CIRCUITS AND METHODS THEREOF

Absstract of: US20260100186A1

0000 Disclosed is a sensor-processing system including, in some embodiments, a sensor, one or more sample pre-processing modules, one or more sample-processing modules, one or more neuromorphic integrated circuits (“ICs”), and a microcontroller. The one or more sample pre-processing modules are configured to process raw sensor data for use in the sensor-processing system. The one or more sample-processing modules are configured to process pre-processed sensor data including extracting features from the pre-processed sensor data. Each of the neuromorphic ICs includes at least one neural network configured to arrive at actionable decisions of the neural network from the features extracted from the pre-processed sensor data. The microcontroller includes a CPU along with memory including instructions for operating the sensor-processing system. In some embodiments, the sensor is a pulse-density modulation (“PDM”) microphone, and the sensor-processing system is configured for keyword spotting. Also disclosed are methods of such a keyword spotting sensor-processing system.

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.

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.

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.

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.

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.

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.

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.

IDENTIFYING ARTIFACTS DIFFERENCES USING GRAPH NEURAL NETWORKS

Absstract of: US20260093717A1

Certain aspects of the disclosure provide for a difference analysis method. In certain aspects, a difference analysis method may include embedding a set of source documents into a knowledge graph, wherein each source document is embedded in the knowledge graph as a set of segments and a set of associations connecting two or more segments. A difference may be determined between a first segment in the set of segments of a first source document and a second segment in the set of segments of a second source document. In response to determining the difference between the first segment in the set of segments of the first source document and the second segment in the set of segments of the second source document, determining a significance of the difference on the second source document based on one or more associations of the set of associations connected to the second segment.

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

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.

DISTRIBUTED CONSTRAINED COMBINATORIAL OPTIMIZATION LEVERAGING HYPERGRAPH NEURAL NETWORKS

Absstract of: US20260093769A1

0000 A method for solving constrained combinatorial optimization task includes receiving data associated with a constrained combinatorial optimization task and optimization variables, the data including a set of constraints defined over subsets of the optimization variables. A hypergraph is constructed based on the set of constraints and optimization variables. Each node and hyperedge of the hypergraph corresponds to an optimization variable and a constraint respectively. A hypergraph neural network is initialized based on the hypergraph and trained using unsupervised learning to output a continuous assignment for each optimization variable. The training includes updating a plurality of learnable input embeddings associated with the nodes and weight parameters of the network. The continuous assignment is then mapped to a discrete assignment selected from a set of discrete values to yield a solution to the constrained combinatorial optimization task.

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.

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 FOR CONDENSING TRAINING DATASET, AND IMAGE PROCESSING DEVICE

Absstract of: US20260087787A1

A method of condensing a training dataset and an image processing device are provided. The method of includes generating a cluster set by clustering a training dataset; generating an initial condensed high-resolution (HR) dataset by selecting, for each cluster included in the cluster set, one or more images from among a respective cluster in the training dataset; obtaining a first loss of a first neural network model based on the training dataset and obtaining a second loss of a second neural network model based on the initial condensed HR dataset. The method further includes generating a condensed HR dataset by updating, based on the first loss and the second loss, pixels in each of the one or more images included in each cluster of the initial condensed HR dataset; and executing an operation instruction to transmit the condensed HR dataset to an image processing device.

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.

Method, System, and Device for Wind Speed Prediction and Layout optimization in Wind Power Generation

Absstract of: US20260085661A1

0000 A method, system, and device for wind speed prediction and layout optimization in wind power generation are provided. The method includes: obtaining a basic wind resource dataset of a target region; constructing a physics-informed neural network model based on the basic wind resource dataset; obtaining wind speeds data at a specific location in a velocity field based on the physics-informed neural networks and constructing a training dataset; training the physics-informed neural network model based on the training dataset; reconstructing a wind speed distribution within the velocity field and predicting wind speeds for a next time period with a wind farm using the trained physics-informed neural network model; and optimizing a layout of a wind turbine cluster based on a reconstructed wind speed distribution within the velocity field. The present application reconstructs a two-dimensional velocity field of the wind farm by training the PINN and enables accurate ultra-short-term wind speed prediction.

MACHINE LEARNING TECHNIQUES FOR GENERATING CONTROLLER LOGIC

Absstract of: US20260086524A1

Embodiments of the present disclosure relate to generating controller logic. Indication of a controller logic generation request associated with an asset identifier may be received. A prompt template set associated with a controller logic generation workflow may be identified based on the asset identifier. The prompt template of the prompt template set may comprise one or more instruction sets. The prompt template set may be input into a large language model comprising one or more transformer neural networks and configured to generate a controller logic configuration file for the asset identifier based on the prompt template set and intent classification associated with each prompt template. The controller logic configuration file may be received from the large language model. Performance of one or more prediction-based actions may be initiated based on the controller logic configuration file.

Neural Networks with Semantic Inference

Absstract of: US20260087304A1

0000 Systems and method of classification are provided. Upon receiving an input, a feature set is defined from the input. A semantic cluster to be associated with the input is defined based on the feature set, the semantic cluster being one of a plurality of semantic clusters each defining a subset of outputs of a neural network based on semantic similarity of the subset. The feature set is applied to a subgraph corresponding to the semantic cluster, the subgraph being one of a plurality of subgraphs each defining a portion of the neural network. A classification for the input is then be determined based on an output of the subgraph.

DEEP LEARNING INTERNAL STATE INDEX-BASED SEARCH AND CLASSIFICATION

Absstract of: US20260088022A1

Systems and methods are disclosed for generating internal state representations of a neural network during processing and using the internal state representations for classification or search. In some embodiments, the internal state representations are generated from the output activation functions of a subset of nodes of the neural network. The internal state representations may be used for classification by training a classification model using internal state representations and corresponding classifications. The internal state representations may be used for search, by producing a search feature from an search input and comparing the search feature with one or more feature representations to find the feature representation with the highest degree of similarity.

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.