Alerta

DATA PROCESSING APPARATUS AND METHOD, AND CHIP, ELECTRONIC DEVICE AND STORAGE MEDIUM

Absstract of: WO2026174872A1

A data processing apparatus, a data processing method, a chip, an electronic device and a computer-readable storage medium. The data processing apparatus comprises a signal processing unit and a neural network processing unit, wherein the signal processing unit is configured with a derivative operator operation strategy, and the neural network processing unit is configured with a neural network model. After the neural network model is updated or modified, operator input data of a preset derivative operator in the neural network model can be sent to the signal processing unit, and by reusing the computing power of the signal processing unit, a derivative operator operation strategy corresponding to the operator input data is executed and an obtained operator operation result is sent to the neural network processing unit.

GENERATIVE AI MODELS USING INDUCTIVE MOMENT MATCHING

Absstract of: WO2026178099A1

Described are methods and systems for training generative artificial intelligence (Al) models. A method for training a generative Al model can include obtaining a first dataset comprising an observed data sample from a data distribution of observed data and a second dataset comprising a prior sample from a prior distribution; synthesizing first data at a first time step based on the observed data sample and the prior sample; synthesizing second data at a second time step based on the observed data sample and the first data; generating, using a neural network, a first output and a second output at the target time step; and obtaining a trained generative Al model by updating parameters of the neural network, wherein the updating comprises at least computing a loss between a first distribution of the first output and a second distribution of the second output.

LEARNING APPARATUS

Absstract of: US20260252891A1

A forward propagation apparatus is a forward propagation apparatus for a neural network, including: a mask generation unit that generates a binary mask; and a layer execution unit that performs an operation for a sparse convolutional layer according to a value at each coordinate of the binary mask, in which the mask generation unit: generates heat maps by performing an operation for a convolutional layer on an input feature map; generates a composite heat map obtained by combining the heat maps, into one heat map by summing up values of heat maps on a coordinate-by-coordinate basis; and generates the binary mask by binarizing a value at each coordinate of the composite heat map by using a predetermined threshold.

MULTISCALE DIMENSIONAL REDUCTION OF DATA

Absstract of: US20260252886A1

In some embodiments, a method includes segmenting updates associated with a record into a set of update subsets and generating first and second vectors based on first and second update subsets using a first neural network. The first update subset is associated with a first session and a timestamp, and the second update subset is associated with a second session. The method includes determining a first output using a second neural network based on the first and second vectors and a time difference between the first and second sessions. The method includes selecting a segment of a periodic time interval based on the timestamp, determining a second output using a third neural network based on a ratio based on the segment and the periodic time interval, and generating a characterizing vector using a fourth neural network based on the first and second outputs.

METHOD FOR OBTAINING A MACHINE LEARNING MODEL FOR ESTIMATION OF TOTAL ORGANIC CARBON (TOC) FROM HYPERSPECTRAL DATA OF ROCK SAMPLES

Absstract of: US20260252966A1

0000 Method for estimating total organic carbon (TOC) of rock samples in an automated manner and without the use of destructive techniques. The technique obtains hyperspectral data from rock samples and trains and uses machine learning algorithms, among them artificial neural networks (ANN), to estimate TOC based on the obtained hyperspectral data. The method described herein may be applied to rock samples from different sedimentary basins, provided that the algorithms are trained with samples from all basins. The method has been shown to be generalizable to other rock samples belonging to the basin or sedimentary basins used in the training of the algorithms. The method eliminates the subjectivity of the human analyst and optimizes the time and resources expended in conventional TOC estimation.

PATCHWISE MULTI-SCALE SIMILARITY ANALYSIS FOR BUILT-ENVIRONMENT STRUCTURE IMAGE LOOKUP ACROSS VARIOUS GEOGRAPHIC SCALES

Absstract of: US20260253376A1

A system and method for analyzing images of built-environment structures at multiple geographic scales using patchwise segmentation and domain-specific embedding. The system extracts image patches at a plurality of spatial scales from imagery, generates patch embeddings via a neural network trained using semi-supervised or unsupervised learning on built-environment structure images, receives a query comprising an example image or textual descriptor, computes similarity scores between query and patch embeddings using a configurable metric, and aggregates scores across scales to produce a composite similarity result. The system supports configurable weighting of scale contributions, overlapping patches for boundary fidelity, hierarchical resolution processing for bandwidth efficiency, feedback-driven model refinement, and deployment across cloud, edge, and hybrid configurations. Applications include material identification, condition assessment, damage detection, and regional trend analysis for roofing and other built-environment structures.

SYSTEMS AND METHODS FOR GENERATING GRAPH DATA STRUCTURES HAVING DIRECTED AND UNDIRECTED EDGES BASED ON DATASETS

Absstract of: US20260252841A1

0000 A method includes providing a semantic vector data as input to a first graph neural network to produce first prediction data for a first time, the first graph neural network including a graph data structure that has (1) a directed edge having a correlation weight and (2) an undirected edge having a causal weight, and the first graph neural network being configured to generate a first aggregation value based on a plurality of weight values associated with a plurality of nodes of the graph data structure. The semantic vector data is provided as input to a second graph neural network to produce second prediction data for a second time, the second graph neural network being produced based on the graph data structure and configured to generate a second aggregation value based on (1) the plurality of weight values and (2) a temporal dependency.

SYSTEMS AND METHODS FOR MULTI-TASK BASELINE MODELS IN SEMICONDUCTOR METROLOGY AND INSPECTION APPLICATIONS

Absstract of: US20260251983A1

Described are systems and methods for unsupervised detection and segmentation of unknown objects in semiconductor metrology and inspection applications. Methods can include receiving a first dataset comprising one or more unknown objects and a second dataset comprising a set of reference objects, generating a set of input embeddings of the one or more unknown objects by applying an encoder to the first dataset, generating a set of correlated embeddings by applying a convolutional neural network (CNN) to the set of input embeddings and reference embeddings, generating a set of reference-attentioned embeddings of the one or more unknown objects, and training a machine learning (ML) model using the output of the reference-attentioned model.

MODEL TRAINING METHOD, WATERMARK TEXT RECOGNITION METHOD, AND RELATED DEVICE

Absstract of: US20260253160A1

0000 Provided in the present application are a model training method, a watermark text recognition method, and a related device. The training method comprises: acquiring watermark style information and background style information, wherein the watermark style information is used for indicating a content style of a visible-watermark character, and the background style information is used for indicating a content style of a background image; generating a watermark image set according to a combination of the watermark style information and the background style information, wherein the watermark image set comprises a plurality of images with visible watermarks; pixelating the watermark images in the watermark image set, extracting pixel values in pixel blocks as training samples, using visible watermarks, which correspond to the watermark images, as sample labels, and combining the training samples with sample labels corresponding thereto, so as to generate a training data set; and constructing a bidirectional recurrent neural network model, and calling the training data set to train the bidirectional recurrent neural network model, so as to obtain a model, which meets a training termination condition, as a watermark restoration model, wherein the watermark restoration model is used for restoring visible-watermark characters in the images.

SPATIAL INFORMATION BASED ANOMALY DETECTION

Absstract of: US20260253200A1

0000 A method for region of interest (ROI) defect detection related to an evaluated manufactured item (MI), the method includes obtaining a reference MI image; obtaining a reference ROI definition; obtaining the evaluated MI image; feeding the reference MI image and the evaluated MI image to a neural network; detecting, by the neural network, one or more geometrical warping operations that once applied on the reference MI image results in an approximation of the evaluated MI image; applying the one or more geometrical warping operations on the reference ROI definition to provide a definition of an evaluated MI image ROI; and applying an ROI-based defect detection process on the evaluated MI image, based on the evaluated MI image ROI.

STATE ESTIMATION APPARATUS, QUESTION RECOMMENDATION APPARATUS, STATE ESTIMATION METHOD, QUESTION RECOMMENDATION METHOD, AND PROGRAM

Absstract of: US20260253506A1

Provided is a technique for recommending a question suitable for use in future study to a learner. Included are a correct answer rate prediction unit that estimates a predicted correct answer rate of a question by using a learned neural network from an input vector obtained from a test result of a learner of K questions or by using a decoder of a learned neural network from a latent variable vector obtained from an input vector obtained from the test result of the learner of the K questions, and a question selection unit that selects a question to be recommended to the learner from among selection candidate questions by using a reference predicted correct answer rate that is a predicted correct answer rate to be a reference for recommending a question to be solved and predicted correct answer rates of the selection candidate questions among the K questions.

VIEW TRANSITION THROUGH NEURAL IMPLICIT MORPHING

Absstract of: US20260252896A1

0000 Matching keypoint pairs are generated and identified in original and rectified image spaces between two input images. A teacher neural network is trained based at least in part on the pairs of matching keypoints in the rectified image space. A neural implicit morphing network is trained jointly with the teacher neural network based at least in part on the matching keypoint pairs in the original image spaces in which predictions outputted from the teacher neural network are used to compute a loss function designated to train the neural implicit morphing network. The neural implicit morphing network on its own, after training, is caused to output intermediate images in the view transition between the two input images.

META-LEARNING NEURAL NETWORK FOR ADAPTIVE PATTERN DETECTION

Absstract of: US20260252903A1

This invention presents a hybrid approach integrating Model-Agnostic Meta-Learning (MAML) with Neural Networks for adaptive and real-time anomaly detection across various domains, including healthcare, cybersecurity, industrial monitoring, and predictive analytics. The Neural Network component captures temporal dynamics and relational structures within high-dimensional data, such as medical imaging scans, network traffic logs, sensor data, and financial transactions, enabling the identification of complex, evolving anomalies. MAML enhances the model's adaptability, allowing it to rapidly generalize to new abnormal patterns with minimal labeled data. This is particularly valuable in detecting rare diseases in medical diagnostics, zero-day cyber threats, equipment failures in industrial systems, and financial fraud in transactional data. The combination of graph-based learning, temporal sequence modeling, and meta-learning ensures high detection accuracy, scalability, and real-time responsiveness, making it a versatile and robust solution for dynamic and complex environments where traditional models struggle to generalize.

Systems and Methods for Decoding Speech from Neural Activity

Absstract of: US20260253589A1

Systems and methods for decoding speech from neural activity in accordance with embodiments of the invention are illustrated. One embodiment includes a brain-computer interface for decoding intended speech including a microelectrode array, a processor communicatively coupled to the microelectrode array, and a memory, the memory containing a speech decoding application that configures the processor to: receive neural signals from a user's brain recorded by a microelectrode array, where the neural signals comprise action potential spikes, bin the received action potential spikes by time, provide the bins to a recurrent neural network (RNN) to receive a likely phoneme at the time of each provided bin, generate an estimated intended speech using a phoneme decoder provided with the likely phonemes, where the phoneme decoder comprises a language model formatted as a weighted finite-state transducer, and vocalize the estimated intended speech using a loudspeaker communicatively coupled to the brain-computer interface.

Self-Explaining Decision Architecture and Methods of Use

Absstract of: US20260252951A1

A Self-Explaining Decision Architecture (SEDA) for machine learning-based decision-making systems capable of generating intuitive explanations for its decisions in real time. SEDA makes use of a feature extraction subsystem and a sequence interpretation subsystem to identify patterns in data followed by a decision generation subsystem that determines appropriate actions based on those patterns. Internal state information from each of these subsystems is used to generate explanations of the system's decisions. Using this information to create explanations provides insight as to the data elements the system focused on when making decisions as well as the reasoning that was used. In at least one embodiment the system uses deep learning components including a combined convolutional neural network and long short-term memory network with attention mechanisms.

REINFORCEMENT LEARNING USING DENSITY ESTIMATION WITH ONLINE CLUSTERING FOR EXPLORATION

Absstract of: US20260252897A1

0000 Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training a neural network used to select actions to be performed by an agent interacting with an environment. Implementations of the described techniques can learn to explore the environment efficiently by storing and updating state embedding cluster centers based on observations characterizing states of the environment.

ELECTRONIC DEVICE FOR PERFORMING VISION PERCEPTION FROM IMAGE ACQUIRED USING META LENS, AND OPERATING METHOD THEREOF

Absstract of: EP4797714A1

An electronic device for performing vision perception from an image acquired using a meta lens, and an operating method thereof are provided. The electronic device according to one embodiment of the present disclosure comprises: a meta lens having a pattern formed on the surface thereof and including a plurality of pillars or pins with different shapes, heights and widths; and an image sensor configured to receive phase-modulated light reflected from an object and transmitted through the meta lens, and obtain a coded image by converting the received light into an electrical signal; and at least one processor configured to input the coded image into an artificial intelligence model, and obtain a label indicating a perception result of an object through inference using the artificial intelligence model, wherein the artificial intelligence model may be a neural network model trained to obtain a simulation image by inputting an RGB image into a model reflecting optical characteristics of the meta lens, and output, as the perception result of the simulation image, a label indicating ground truth of the RGB image that was input.

COMPUTER-IMPLEMENTED METHOD FOR APPROXIMATING AT LEAST TWO UNKNOWN VARIABLES OF A SET OF PARTIAL DIFFERENTIAL EQUATIONS, HYBRID COMPUTING SYSTEM, COMPUTER PROGRAM PRODUCT AND COMPUTER-READABLE MEDIUM

Absstract of: EP4797152A1

The invention relates to a computer-implemented method for approximating at least two unknown variables (10) of a set of partial differential equations using a quantum physics-informed neural network (100), the method comprising the steps: providing a numerical grid (20) having grid coordinates (30) at which the unknown variables (10) are to be approximated; providing a quantum physics-informed neural network (100), the quantum physics-informed neural network (100) comprising a hybrid network (110) for each unknown variable (10), wherein the hybrid networks (110) are not interconnected to each other, each hybrid network (110) having a quantum network (120) having at least one quantum layer (130) and a classical network (140) having at least one classical layer (150), wherein the respective quantum network (120) and the respective classical network (140) are not interconnected; inputting the grid coordinates (30) into the quantum physics-informed neural network (100), such that the grid coordinates (30) are input to each hybrid network (110); and computing the output (H_out) of each hybrid network (110) for each grid coordinate (30), each output (H_out) corresponding to a different unknown variable (10) to be approximated at the grid coordinate (30), wherein the output (H_out) of each hybrid network (110) is obtained by combining an output of the respective quantum network (Q_out) and an output of the respective classical network (C

DYNAMICALLY PREDICTING SHOT TYPE USING A PERSONALIZED DEEP NEURAL NETWORK

Absstract of: EP4796194A2

A computing system retrieves ball-by-ball data for a plurality of sporting events. The computing system generates a trained neural network based on ball-by-ball data supplemented with ball-by-ball data with ball-by-ball match context features and personalized embeddings based on a batsman and a bowler for each delivery. The computing system receives a target batsman and a target bowler for a pitch to be delivered in a target event. The computing system identifies target ball-by-ball data for a window of pitches preceding the to be delivered pitch. The computing system retrieves historical ball-by-ball data for each of the target batsman and the target bowler. The computing system generates personalized embeddings for both the target batsman and the target bowler based on the historical ball-by-ball data. The computing system predicts a shot type for the pitch to be delivered based on the target ball-by-ball data and the personalized embeddings.

GENERATING AUDIO USING GENERATIVE NEURAL NETWORKS

Absstract of: WO2025109032A2

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating audio and, optionally, a corresponding image using generative neural networks. For example, a spectrogram of the audio can be generated using a hierarchy of diffusion neural networks.

END-TO-END CAMERA CALIBRATION FOR BROADCAST VIDEO

Absstract of: EP4797161A2

A system and method of calibrating a broadcast video feed are disclosed herein. A computing system retrieves a plurality of broadcast video feeds that include a plurality of video frames. The computing system generates a trained neural network, by generating a plurality of training data sets based on the broadcast video feed and learning, by the neural network, to generate a homography matrix for each frame of the plurality of frames. The computing system receives a target broadcast video feed for a target sporting event. The computing system partitions the target broadcast video feed into a plurality of target frames. The computing system generates for each target frame in the plurality of target frames, via the neural network, a target homography matrix. The computing system calibrates the target broadcast video feed by warping each target frame by a respective target homography matrix.

GRAPH NEURAL NETWORK AND TRANSFORMER-BASED TASK PLANNER

Absstract of: US20260245041A1

Disclosed is a graph neural network (GNN) and transformer-based task planner. A task planning method performed by a task planning system may include constructing a task planner model based on a graph neural network and a transformer; and generating a task plan from a goal instruction of a task and history information of a scene graph through the constructed task planner model.

SYSTEMS AND METHODS FOR ENTROPY-BASED PRUNING OF NEURAL NETWORK MODELS

Absstract of: US20260244926A1

Embodiments described herein provide a method for hardware resource allocation during the operation of a generative neural network model. The method includes receiving a set of input data at a neural network-based model implemented on one or more hardware processors, where the model comprises a plurality of sequentially connected blocks. The method involves computing respective input and output intermediate values for at least one block during forward passes of the model, and calculating a change in entropy for each block based on the difference between entropy estimates for the input and output intermediate values. Blocks are pruned based on their respective changes in entropy, and hardware resources allocated to the pruned model are adjusted accordingly. The pruned neural network model is then operated using the adjusted hardware resources.

DATA PROCESSING METHOD AND APPARATUS, DEVICE, AND MEDIUM

Absstract of: US20260244898A1

Provided in the present disclosure are a data processing method and apparatus, device, and medium. The method includes: inputting data to be processed into a target neural network for processing to obtain a processing result of the data to be processed, at least one convolution layer of the target neural network being an attention convolution layer based on a first attention mechanism, and/or, performing feature fusion between at least two levels of convolution layers of the target neural network on the basis of a second attention mechanism, the first attention mechanism including a self-attention mechanism for a local area of a feature, and the second attention mechanism including an attention mechanism for a local area of an output feature between output features of different scales.

SYSTEMS AND METHODS FOR CONTENT ADAPTIVE MULTI-SCALE FEATURE LAYER FILTERING AND REDUNDANT CHANNEL PROCESSING

Nº publicación: US20260246928A1 20/08/2026

Applicant:

OP SOLUTIONS LLC [US]
OP Solutions LLC

Absstract of: US20260246928A1

0000 Systems and methods are provided for encoding and decoding video for machine consumption in which bandwidth is reduced by filtering feature layers and filtering channels at the encoder site that are determined to be redundant or of reduced relevance. A video encoder includes a neural network front end which receives image data and generates a plurality of feature layers. The relevance of the plurality of feature layers to a machine task at the decoder site is determined and redundant layers can be removed. Channels in at least one feature layer can be evaluated for redundancy and redundant channels also removed prior to encoding.