Alerta

USING NEURAL NETWORKS TO GENERATE IMAGES

Resumen de: US20260289736A1

0000 Apparatuses, systems, and techniques to blend two or more images based on confidence values of objects within said two or more images. In at least one embodiment, one or more confidence values in one or more images are generated using one or more neural networks that are used, for example, to blend two or more images to be displayed.

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

Resumen de: US20260289053A1

The invention relates to a shale fracture seismic identification method based on a 3D U-Net convolutional neural network combined with ant tracking. 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.

METHOD FOR TRAINING A NEURAL NETWORK TO CONTROL A TECHNICAL SYSTEM

Resumen de: US20260289299A1

0000 A method for training a neural network to control a technical system. The method includes ascertaining a partitioning of a control function operating on an input space into a set of first affine functions, each operating on a particular first subset of the input space; training the neural network to approximate the control function in a plurality of iterations, comprising, for each iteration: ascertaining, for each first subset, how the neural network partitions the first subset into second subsets such that it behaves like a particular second affine function on each second subset; ascertaining, for each of the second subsets, an approximation error between the neural network and the control function; ascertaining an overall approximation error between the neural network and the control function from the ascertained approximation errors; and adapting the neural network to reduce the overall approximation error.

THREE-DIMENSIONAL INTERSECTION STRUCTURE PREDICTION FOR AUTONOMOUS DRIVING APPLICATIONS

Resumen de: US20260285315A1

0000 In various examples, a three-dimensional (3D) intersection structure may be predicted using a deep neural network (DNN) based on processing two-dimensional (2D) input data. To train the DNN to accurately predict 3D intersection structures from 2D inputs, the DNN may be trained using a first loss function that compares 3D outputs of the DNN—after conversion to 2D space—to 2D ground truth data and a second loss function that analyzes the 3D predictions of the DNN in view of one or more geometric constraints—e.g., geometric knowledge of intersections may be used to penalize predictions of the DNN that do not align with known intersection and/or road structure geometries. As such, live perception of an autonomous or semi-autonomous vehicle may be used by the DNN to detect 3D locations of intersection structures from 2D inputs.

METHOD AND APPARATUS FOR ENHANCING SPEECH USING ARTIFICIAL INTELLIGENCE

Resumen de: US20260290366A1

0000 In a speech enhancement method performed by an electronic device using artificial intelligence according to an embodiment of the present disclosure, the method may include: determining a hidden representation for a sequence of an input speech signal in a first neural network; determining speech recognition information based on the hidden representation; receiving the speech recognition information and an input data block in a second neural network; and generating an output data block by combining the speech recognition information and the input data block. (FIG. 8)

METHOD AND APPARATUS WITH OBJECT ESTIMATION MODEL TRAINING

Resumen de: US20260289311A1

A method and apparatus with object estimation model training is provided. The method include generating a cross-correlation loss based on a first feature vector, generated using an interim first neural network (NN) model provided an input based on first input data about a target object, and a second feature vector generated using a trained second neural network provided another input based on second input data about the target object; and generating a trained first NN model, including training the interim first NN model based on the cross-correlation loss.

Predictive Access Control for Application Programming Interfaces Using Non-Fungible Token Bindings and Recurrent Neural Network Forecasting of Performance Metrics

Resumen de: US20260289563A1

Cryptographic control regulates access by DevOps computing to an API service through an API gateway. A processor applies a long short term memory neural network to a plurality of performance metrics of the application programming interface service in real-time, the plurality of performance metrics including a time to first hello world value, a request per minute count, an average latency value, a maximum latency value, an errors per minute count, an application programming interface uptime value, a memory usage value, and a central processing unit usage value. The long short term memory neural network produces a forecast output predicting a future value of at least one of the plurality of performance metrics. When the forecast output indicates the future value is outside a predetermined performance range, the processor disables access in accordance with a smart contract bound to a non-fungible token. A non-fungible token repository data structure is dynamically updated.

IMAGE GENERATION USING ONE OR MORE NEURAL NETWORKS

Resumen de: US20260289296A1

Apparatuses, systems, and techniques are presented to generate image or video content. In at least one embodiment, one or more neural networks are used to generate one or more time-lapsed images of a second object based, at least in part, on one or more images of a first object.

TECHNIQUES TO USE A NEURAL NETWORK TO EXPAND AN IMAGE

Resumen de: US20260289724A1

0000 Apparatuses, systems, and techniques for texture synthesis from small input textures in images using convolutional neural networks. In at least one embodiment, one or more convolutional layers are used in conjunction with one or more transposed convolution operations to generate a large textured output image from a small input textured image while preserving global features and texture, according to various novel techniques described herein.

DATA FOR MACHINE LEARNING MODELS

Resumen de: US20260290075A1

A machine learning model (MLM) may be trained and evaluated. Attribute-based performance metrics may be analyzed to identify attributes for which the MLM is performing below a threshold when each are present in a sample. A generative neural network (GNN) may be used to generate samples including compositions of the attributes, and the samples may be used to augment the data used to train the MLM. This may be repeated until one or more criteria are satisfied. In various examples, a temporal sequence of data items, such as frames of a video, may be generated which may form samples of the data set. Sets of attribute values may be determined based on one or more temporal scenarios to be represented in the data set, and one or more GNNs may be used to generate the sequence to depict information corresponding to the attribute values.

APPARATUS AND METHOD FOR ADAPTIVE IMAGE SCALING AND OBJECT TRACKING USING NPU

Resumen de: US20260289809A1

0000 An electronic device mounted on a fixed or a movable apparatus is provided. The electronic device may comprise a neural processing unit (NPU), including a plurality of processing elements (PEs), configured to process an operation of an artificial neural network model trained to detect or track at least one object and output an inference result based on at least one image acquired from at least one camera; and a signal generator generating a signal applicable to the at least one camera.

FEATURE MAP COMPRESSION METHOD AND APPARATUS

Resumen de: US20260292179A1

0000 A neural network-based image processing method and apparatus according to an embodiment of the present invention may: acquire a feature tensor from an input image by using a first neural network including a plurality of neural network layers; acquire a symbol tensor by performing quantization on the acquired feature tensor; and generate a bitstream by performing entropy encoding on the basis of the symbol tensor.

Anomaly Detection Using Hybrid Neural Network Framework

Resumen de: US20260291963A1

0000 A hybrid quantum-classical framework detects anomalies in network data by integrating quantum and classical neural networks. Data acquisition collects user inputs and network traffic, forming a raw dataset preprocessed with SHA3 hashing and SPHINCS+ quantum-safe signatures for integrity. Quantum encoding with BB84 QKD and CNOT gate entanglement secures quantum transfers, while a quantum neural network validates data, normalizes it, and applies amplitude encoding to extract features using variational quantum circuits with RY/RZ gates, optimized via gradient descent. A variational quantum recurrent network with quantum memory classifies anomalies, thresholding scores at 0.9 to generate severity-ranked alerts. A classical convolutional neural network analyzes spatial patterns, with a multi-translation layer fusing quantum and classical outputs. An integration module combines results, adjusts circuit depth, monitors latency, and logs anomalies to persistent storage, ensuring real-time, comprehensive anomaly detection across diverse network environments.

GENERALIZATION CAPABILITY FOR AI-BASED CHANNEL ESTIMATION VIA MIXTURE OF EXPERTS

Resumen de: US20260291781A1

A method includes receiving, by a first electronic device, a signal from a second electronic device over a channel. The method further includes preprocessing, by the first electronic device, the signal to generate a noisy channel estimate. The method additionally includes estimating, by the first electronic device, the channel based on the noisy channel estimate using a neural network having a mixture of experts (MoE) architecture and a router.

FIXED-POINT MULTIPLICATION FOR NETWORK QUANTIZATION

Resumen de: US20260289307A1

0000 Techniques for training a neural network having a plurality of computational layers with associated weights and activations for computational layers in fixed-point formats include determining an optimal fractional length for weights and activations for the computational layers; training a learned clipping-level with fixed-point quantization using a PACT process for the computational layers; and quantizing on effective weights that fuses a weight of a convolution layer with a weight and running variance from a batch normalization layer. A fractional length for weights of the computational layers is determined from current values of weights using the determined optimal fractional length for the weights of the computational layers. A fixed-point activation between adjacent computational layers is related using PACT quantization of the clipping-level and an activation fractional length from a node in a following computational layer. The resulting fixed-point weights and activation values are stored as a compressed representation of the neural network.

CROSS SPLINE NETWORK

Resumen de: US20260289281A1

A computer system for machine learning-based prediction is disclosed. The system applies a neural network-based spline transformation to input variables to generate transformed features. The transformed features are processed using a cross network comprising one or more cross layers, each configured to model feature interactions by combining prior layer outputs with learned weight parameters and applying a “cross” (multiplication) transformation with the input features. An output prediction is generated based on the transformed features processed by the cross network. The disclosed approach enables improved modeling of feature interactions while leveraging neural network-based transformations, facilitating enhanced interpretability and computational efficiency in machine learning applications.

SYSTEMS AND METHODS FOR REGULARIZATION OF SEISMIC MIGRATION USING A GENERATIVE DIFFUSION MODEL

Resumen de: US20260289045A1

0000 This disclosure provides methods for regularization of seismic migration using generative diffusion modelling (GDM) and systems for performing the same. For example, methods may include constructing one or more denoising diffusion probabilistic models based on seismic information. Methods may include training a neural network based on the one or more denoising diffusion probabilistic models (DDPMs) and the loss function of an evidence lower bound (ELBO). Methods may include applying the neural network to a reflectivity profile constructed using the seismic information to construct at least one refined seismic representation. Applying the neural network to the reflectivity profile may regularizing a first iterative portion of the reflectivity profile using the neural network, updating the reflectivity profile based on a learning rate value, and regularizing a second iterative portion of the reflectivity profile using the neural network.

SYSTEM AND METHOD FOR AUTOMATED MACHINE LEARNING MODEL TRAINING

Resumen de: US20260289326A1

A system for automated machine learning model training comprising processor configured to receive multi-modal training data and user-defined parameters through end-user abstraction interface, autonomously determine machine learning domain applicable to multi-modal input data by analyzing data annotations. Autonomously prune redundant data elements from multi-modal input data to generate training dataset, automatically identify hyperparameters for training dataset, automatically split multi-modal input data into plurality of data groups using dynamically determined split ratios. Select a machine learning framework and neural network architecture based on the determined machine learning domain. Perform batch normalization on training dataset, train machine learning model using training dataset, selected framework and architecture, and identified hyperparameters, training includes dynamic adjustment of learning rates and evaluate machine learning model during training using validation data from plurality of data groups, wherein training is terminated when loss function indicates minimal reduction in difference between actual and predicted value.

LOW POWER ANALOG CIRCUITRY FOR ARTIFICIAL NEURAL NETWORKS

Resumen de: US20260290329A1

0000 A low power analog Long Short-Term Memory (LSTM) recurrent neural network has an input layer, an array of Adaptive Filter Unit for Analog LSTM, a linear projection layer, and an output layer. The output layer has multiple nonlinear amplifiers, a nonlinear element with a sigmoidal input-output characteristic function, and a time-constant adjustable, nonlinear, low pass filter that provides the memory function of the LSTM. The LSTM memory is used with mismatch-robust weights determined by learning by computation of optimal weights values, wherein the objective function minimizes misdetection probability, and used to process a signal to detect events.

DISTRIBUTED NEURAL NETWORK TRAINING SYSTEM

Resumen de: US20260288904A1

Apparatuses, systems, and techniques to train a machine-learned model. In at least one embodiment, a plurality of training clients each obtain an exclusive right to update a model in turn, and each client trains said model with training data not accessible to other training clients.

VIDEO SYNTHESIS WITHIN A MESSAGING SYSTEM

Resumen de: US20260289238A1

0000 Aspects of the present disclosure involve a system comprising a computer-readable storage medium storing a program and method for video synthesis. The program and method provide for accessing a primary generative adversarial network (GAN) comprising a pre-trained image generator, a motion generator comprising a plurality of neural networks, and a video discriminator; generating an updated GAN based on the primary GAN, by performing operations comprising identifying input data of the updated GAN, the input data comprising an initial latent code and a motion domain dataset, training the motion generator based on the input data, and adjusting weights of the plurality of neural networks of the primary GAN based on an output of the video discriminator; and generating a synthesized video based on the primary GAN and the input data.

INTERACTIVE ALARM

Resumen de: US20260288131A1

Industrial sites utilize process components, or "tags," to perform, monitor, and control industrial processes. When an alarm occurs, it can be critical to quickly execute an action to best resolve the alarm. Providing an operator with a prioritized list of recommended actions to a particular alarm enables the user to quickly identify and take the recommended action to resolve the alarm. The recommendation may be determined by an artificial intelligence, such as a trained neural network, analyzing process components and their interrelationships associated with an alarm.

INFERENCE OF CARTILAGE SEGMENTATION IN COMPUTED TOMOGRAPHY SCANS

Resumen de: US20260289948A1

Some examples are directed to a processor-implemented methods of training a neural network for soft-tissue labeling of computed tomography (CT) images, neural networks trained according to one or more of the processor-implemented methods, processor-implemented methods of soft-tissue-labeling a CT image, and systems for labeling soft-tissue in computed tomography images.

DEFECT DETECTION SYSTEM FOR MOBILE DEVICE COSMETIC INSPECTION

Resumen de: WO2026198555A1

A system may detect cosmetic defects on mobile device surfaces during automated processing. An imaging device may capture images of a mobile device surface under one or more lighting conditions while the mobile device is positioned within an inspection cell. A lighting component may provide the lighting conditions. A defect detection model comprising a convolutional neural network may process the captured images to generate a segmentation output identifying defect regions. The convolutional neural network may be trained on a dataset comprising real images with segmentation masks and synthetic images generated using three-dimensional rendering. The captured images may be received and processed by the defect detection model to generate the segmentation output, and a composite image of the mobile device surface indicating detected defects may be generated. The composite image may include visual indications of defect locations and associated metadata such as defect type, location, and severity characteristics.

METHOD AND SYSTEM FOR SINGLE PASS OPTICAL CHARACTER RECOGNITION

Nº publicación: US20260289995A1 24/09/2026

Solicitante:

TRICENTIS GMBH [AT]
Tricentis GmbH

Resumen de: US20260289995A1

A computer implemented method of performing single pass optical character recognition (OCR) including a fully convolutional neural network (FCN) engine including at least one processor and at least one memory, the at least one memory including instructions that, when executed by the at least processor, cause the FCN engine to perform a plurality of steps. The method includes preprocessing an input image having machine printed characters; extracting two or more image features using a plurality of convolutional layers in the FCN engine; transforming feature maps from the plurality of convolutional layers to a size of the input image using a transposed convolution layer of the FCN engine; generating a multi-channel pixel-level probability output based on the transformed feature maps; scaling the multi-channel pixel-level probability output; generating word boxes for the machine printed characters; determining each character of the machine printed characters; and transmitting, for display, the machine printed characters.