Alerta

FUNCTIONAL ACTIVATION-BASED ANALYSIS OF DEEP NEURAL NETWORKS

Resumen de: US20250148285A1

0000 Functional activation-based analysis of deep neural networks uses a structured set of inputs (e.g., input datasets corresponding to different knowledge or datatype domains) are sequentially provided to a pretrained neural network (e.g., according to a block-sequence). The output values for each node in the neural network are recorded and stored as a time-series of layer output values. A statistical analysis of the time-series of layer output values may be fit as a function of the structured set of inputs to generate neural network analysis data that indicate activations of layers within the neural network based on the inputs.

GENERATING AUDIO USING AUTO-REGRESSIVE GENERATIVE NEURAL NETWORKS

Resumen de: EP4804179A2

0001 Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating a prediction of an audio signal. One of the methods includes receiving a request to generate an audio signal; obtaining a semantic representation of the audio signal; generating, using one or more generative neural networks and conditioned on at least the semantic representation, an acoustic representation of the audio signal; and processing at least the acoustic representation using a decoder neural network to generate the prediction of the audio signal.

RISK ASSESSMENT OF ROTOR ANGLE INSTABILITY IN A POWER NETWORK

Resumen de: EP4804364A1

Rotor angle instability is a key criterion of dynamic stability in power networks. State-of-the-art machine-learning approaches are difficult to scale and have limited inputs with which to make predictions as to rotor angle instability. Accordingly, disclosed embodiments utilize a machine-learning model that is applied to bus voltage angles, which are local quantities available at every bus in the power network, to derive a prediction of the risk of rotor angle stability in the power network. These predictions may be biased in order to avoid false negatives. The machine-learning model may be a message-passing neural network. The resulting predictor is capable of quickly and reliably flagging potential rotor instability within a power network.

CONTROL SYSTEM TESTING UTILIZING RULEBOOK SCENARIO GENERATION

Resumen de: US20260257689A1

0000 Provided are methods for testing of a control system of a vehicle using generated rulebook based scenarios, which can include determining a simulated environment, receiving a hierarchical plurality of autonomous vehicle rules, determining a trajectory of a simulated vehicle within the simulated environment, generating a plurality of simulated scenarios for the simulated vehicle, identifying at least one violation of at least one autonomous vehicle rule by the simulated vehicle in a set of the simulated scenarios, determining a scenario score for each simulated scenario based on the violations, and identifying at least one simulated scenario for a trained neural network of a vehicle based on the scenario scores.

IMAGE PROCESSING METHOD USING NEURAL NETWORK MODEL, AND ELECTRONIC DEVICE FOR PERFORMING SAME

Resumen de: US20260260316A1

An image processing method using a neural network model, and an electronic device are provided. The method may comprise: acquiring a low-resolution image; extracting, from the low-resolution image, luminance information through a luminance channel; acquiring a first feature vector on the basis of the luminance information by using the neural network model to which a first weight is applied; acquiring an output image from the first feature vector by using the neural network model to which a second weight is applied; and generating, on the basis of the output image, a high-resolution image with respect to the low-resolution image. The first weight and the second weight can be different.

DEEP LEARNING SYSTEM

Resumen de: US20260260113A1

0000 A machine learning system is provided to enhance various aspects of machine learning models. In some aspects, a substantially photorealistic three-dimensional (3D) graphical model of an object is accessed and a set of training images of the 3D graphical mode are generated, the set of training images generated to add imperfections and degrade photorealistic quality of the training images. The set of training images are provided as training data to train an artificial neural network.

TARGET DETECTION METHOD AND APPARATUS, DEVICE, AND STORAGE MEDIUM

Resumen de: US20260260447A1

The present application relates to a target detection method and apparatus, a device, and a storage medium. A main technical solution includes: acquiring video set data, inputting the video set data to a backbone network to obtain video frame feature data, inputting the video frame feature data to a convolutional neural network to obtain candidate box data of a target object, optimizing the candidate box data of the target object according to a preset uncertainty estimation loss model to obtain candidate box feature data, and inputting the candidate box feature data to a preset cross-frame and cross-view model for updating and then outputting to obtain a target box and corresponding target detection data.

Tunable Hybrid Neural Video Representations

Resumen de: US20260261689A1

0000 There is provides a neural network-based video decoding method including receiving a latent feature corresponding to a compressed version of a first video frame of a first plurality of a plurality of video frames included in a video content, the latent feature being a combination of a weighted frame-specific embedding of the first video frame with weighted one or more group-of-pictures (GOP) features of the first plurality of the plurality of video frames, wherein the weighted frame-specific embedding is a product of applying a first weight to a frame-specific embedding and the weighted one or more GOP features are products of applying a second weight to the one or more GOP features, wherein the first weight and the second weight are selected as levers for content-specific fine-tuning. The method also including decoding the latent feature to provide an uncompressed video frame corresponding to the first video frame

MACHINE PERCEPTION

Resumen de: US20260260498A1

A deep neural network(s) (DNN) may be used to detect objects from sensor data of a three dimensional (3D) environment. For example, a multi-view perception DNN may include multiple constituent DNNs or stages chained together that sequentially process different views of the 3D environment. An example DNN may include a first stage that performs class segmentation in a first view (e.g., perspective view) and a second stage that performs class segmentation and/or regresses instance geometry in a second view (e.g., top-down). The DNN outputs may be processed to generate 2D and/or 3D bounding boxes and class labels for detected objects in the 3D environment. As such, the techniques described herein may be used to detect and classify animate objects and/or parts of an environment, and these detections and classifications may be provided to an autonomous vehicle drive stack to enable safe planning and control of the autonomous vehicle.

DECISION MANAGEMENT SYSTEM

Resumen de: WO2026180856A1

A computer implemented method for decision management, which utilizes the decision management system as described herein. In the computer implemented method a problem statement input is received. A large language model business knowledge base is searched for a set of top relevant results. The large language model business knowledge base is a trained neural network aggregating proprietary business information and non-proprietary business information from multiple sources. At least a partial feasibility report is automatically constructed responsive to the problem statement for the top relevant results using the large language model business knowledge base.

OUTLIER CORRECTION SERVER AND METHOD USING WINDOW CORRELATION MATRIX, AND SYSTEM INCLUDING SAME

Resumen de: WO2026182308A1

The present invention relates to an outlier correction server and method using a data correction technique utilizing a long short-term memory (LSTM)-based variational autoencoder-generative adversarial network (VAE-GAN) model to effectively improve the quality of multivariate time-series data, and to a system including same. The outlier correction server comprises a memory storing at least one instruction and at least one processor that executes the at least one instruction, wherein the processor collects input data, preprocesses the input data to generate a preprocessing result, and detects an outlier from the preprocessing result by using a pre-trained neural network model.

Computer Vision Based Two-Stage Surgical Phase Recognition Module

Resumen de: US20260260488A1

0000 A system and method of identifying an adverse event using a video of a surgery and a two-stage surgical phase recognition module. The method includes receiving, by the module, a video of the surgery, where the video comprises a sequence of video frames. The module comprises a first stage that includes a neural network and a second stage that includes a multi-stage temporal convolution network. The method includes extracting, using the first stage, visual information content of a single frame based on the single frame; identifying, using the second stage, surgical phases captured in the frames of the video based on the visual information content from the first stage; and identifying, using the identified surgical phases, an adverse event during the surgery. An adverse event includes the omission of a surgical phase and an injury to the patient. The identification can occur in real-time or near-real-time.

Systems and Methods for Digitally Transforming Economic, Organizational and/or Industrial Content and/or Processes

Resumen de: US20260260401A1

Various embodiments of the teachings herein include systems for automatically transforming economic, organizational, and/or industrial content and/or processes capturable by natural language into a digital representation. An example includes: modules for capturing and/or recording user-specific data; processors to process captured data for forwarding to an AI and create digital representations in a recording language; an interface to a second processor associated with a neural network having an AI trained to carry out pattern analysis, pattern recognition, and/or pattern prediction on the basis of the processed user-specific recording data; and a second interface to transmit results from the data editing of the AI to the first processor to generate a digital representation made available to the user via a display module.

MACHINE-LEARNING APPARATUS AND METHOD FOR IMPLEMENTING ARTIFICIAL INTELLIGENCE EDGE DEVICE BY USING RESISTIVE ELEMENTS, AND ANALYSIS APPARATUS AND METHOD USING SAME

Resumen de: US20260260106A1

A learning apparatus and method for implementing an edge device using a resistive element and an analysis apparatus and method using the same are disclosed. The learning apparatus for implementing an edge device using a resistive element according to an embodiment of the present application may include a first learning unit determining a weight of an artificial neural network through learning based on first training data and reflecting the determined weight in a first resistive element, and a second learning unit updating the weight of the artificial neural network through learning based on second training data collected through the device and reflecting the updated weight in the second resistive element.

NETWORK BASED IMAGE FILTERING FOR VIDEO CODING

Resumen de: US20260261668A1

0000 A method and an apparatus for image filtering in video coding using a neural network are provided. The method includes generating a deblocking strength map indicating boundaries of prediction blocks or partition blocks. The deblocking strength map is input into a neural network, and the neural network filters an input frame based on the deblocking strength map.

INTERFACE TRANSLATION USING ONE OR MORE NEURAL NETWORKS

Resumen de: US20260260475A1

0000 Apparatuses, systems, and techniques are presented to generate one or more interfaces. In at least one embodiment, one or more neural networks are used to generate one or more second graphical user interfaces based, at least in part, on one or more functional features of one or more first graphical user interfaces.

DYNAMICALLY DIVIDING ACTIVATIONS AND KERNELS FOR IMPROVING MEMORY EFFICIENCY

Resumen de: US20260260115A1

Embodiments are generally directed to dynamically dividing activations and kernels for improving memory efficiency. An embodiment of a method in a compute engine performing machine learning comprises: receiving, by a convolutional layer of a convolutional neural network (CNN) implemented on the compute engine, a plurality of activation groups contained in an input data, wherein the convolutional layer includes one or more kernel groups and the one or more kernel groups each include a plurality of kernels; determining a plurality of memory efficiency metrics based on the number of activation groups of the plurality of activation groups and the number of kernels of the plurality of kernels; selecting a first optimal number of activation groups and a second optimal number of kernels that are associated with an optimal memory efficiency metric in the plurality of memory efficiency metrics; and performing a convolutional operation on the input data based on the first optimal number and the second optimal number.

SYSTEM, METHOD, AND COMPUTER PROGRAM PRODUCT FOR MACHINE UNLEARNING ON IDENTITY GRAPH NEURAL NETWORKS

Resumen de: WO2025090089A1

Systems, methods, and computer program products for machine unlearning on identity graph neural networks may obtain an identity graph including a plurality of graphs, each graph including a plurality of edges and a plurality of nodes for the plurality of edges, and, in each graph, each edge and each node is associated with a same identity; apply at least one edge augmentation algorithm to the identity graph to make the identity graph a biconnected identity graph; split the biconnected identity graph into a plurality of biconnected components, such that there are no articulation points in each biconnected component; for each biconnected component, train a graph neural network that corresponds to that biconnected component to generate a graph embedding and a local minima; train an ensemble neural network on the graph embedding and the local minima of each biconnected component; and provide the trained ensemble neural network.

SAFE AND EFFICIENT MOTION PLANNING FOR AUTONOMOUS SYSTEMS USING HAMILTON-JACOBI REACHABILITY

Resumen de: US20260249882A1

0000 A method and system are provided for safe motion planning of an autonomous system using a neural-network-based approximation of a Hamilton-Jacobi (HJ) value function. The method includes computing signed distance fields (SDFs) from occupancy grid maps, deriving temporal differences between SDFs, and using these differences as input to a hypernetwork that generates parameters for a main network. The main network computes a residual of the HJ value function, which is modified using a leaky rectified linear unit and combined with a selected SDF to form an intermediate value function. A state-dependent slack function is added to produce a final HJ value function, which is used as a safety constraint in motion planning. The system enables real-time, adaptive, and robust planning in dynamic and partially observable environments.

IDENTIFYING ARTIFACTS DIFFERENCES USING GRAPH NEURAL NETWORKS

Resumen de: US20260252589A1

0000 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.

DISTRIBUTED WEIGHT UPDATE FOR BACKPROPAGATION OF A NEURAL NETWORK

Resumen de: US20260252889A1

0000 Speed of training a neural network is improved by updating the weights of the neural network in parallel. In at least one embodiment, after back propagation, gradients are distributed to a plurality of processors, each of which calculate a portion of the updated weights of the neural network.

Object-Centric Learning with Slot Attention

Resumen de: US20260252870A1

A method involves receiving a perceptual representation including a plurality of feature vectors, and initializing a plurality of slot vectors represented by a neural network memory unit. Each respective slot vector is configured to represent a corresponding entity in the perceptual representation. The method also involves determining an attention matrix based on a product of the plurality of feature vectors transformed by a key function and the plurality of slot vectors transformed by a query function. Each respective value of a plurality of values along each respective dimension of the attention matrix is normalized with respect to the plurality of values. The method additionally involves determining an update matrix based on the plurality of feature vectors transformed by a value function and the attention matrix, and updating the plurality of slot vectors based on the update matrix by way of the neural network memory unit.

GENERATING FRAMES FOR NEURAL SIMULATION USING ONE OR MORE NEURAL NETWORKS

Resumen de: US20260252876A1

Apparatuses, systems, and techniques to use one or more neural networks to generate one or more images based, at least in part, on one or more spatially-independent features within the one or more images. In at least one embodiment, the one or more neural networks determine spatially-independent information and spatially-dependent information of the one or more images and process the spatially-independent information and the spatially-dependent information to generate the one or more spatially-independent features and one or more spatially-dependent features within the one or more images.

LEARNING APPARATUS

Resumen de: 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

Nº publicación: US20260252886A1 27/08/2026

Solicitante:

CAPITAL ONE SERVICES LLC [US]
Capital One Services, LLC

Resumen de: 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.