Redes Neuronais

METHOD AND SYSTEM FOR ZERO-SHOT SPEAKER-ADAPTIVE SPEECH SYNTHESIS

Resumen de: US20260237377A1

0000 There is provided a method for synthesizing a speech waveform from text data. The method comprises: determining, from the text data, a phoneme sequence; obtaining a reference speech waveform comprising a high-level speech representation of a reference speaker speaking a reference speech; applying a trained neural network to the high-level speech representation to extract speaker embeddings; and determining, from the speaker embeddings and the phoneme sequence, a synthesized speech waveform indicative of the reference speaker speaking the text data.

SUBJECT-DRIVEN DIFFUSION NEURAL NETWORKS

Resumen de: US20260237019A1

0000 Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating images of a new subject using a diffusion neural network.

AI-BASED METHOD AND SYSTEM FOR AUTOMATIC OPTIMIZATION OF DISTRIBUTED COMPUTING TASKS FOR BIG DATA

Resumen de: WO2026165976A1

The present invention relates to the technical field of AI, and provides an AI-based method and system for automatic optimization of distributed computing tasks for big data. The method comprises: constructing a multi-modal spatiotemporal feature perception network to extract spatiotemporal features of tasks and resources, and training a hierarchical hybrid decision network to perform global task scheduling and local resource allocation. A hierarchical deep reinforcement learning architecture is used for a global policy network, which combines Monte Carlo tree search and prioritized experience replay to generate decisions. A local execution network optimizes local deployment on the basis of a graph neural network and multi-agent collaborative learning. In addition, a distributed anomaly detection network is deployed to monitor performance in real time, adaptive tuning is achieved by means of reinforcement transfer learning, and finally the perception network is updated by means of knowledge distillation, thereby achieving model evolution. The present invention can effectively improve the execution efficiency and resource utilization rate of distributed computing tasks for big data, and reduce system operation costs.

CAMERA-SPECIFIC EMBEDDINGS IN BIRDS-EYE-VIEW NEURAL NETWORK

Resumen de: US20260237189A1

0000 An apparatus for processing image data includes a memory for storing the image data and processing circuitry in communication with the memory. The processing circuitry is configured to obtain image data including a current set of multiple camera images from multiple cameras. According to such an example, the apparatus may also generate respective feature vectors from each of the multiple camera images with a shared image feature encoder using camera-specific positional embeddings associated with different respective cameras used to capture the multiple camera images. The apparatus may also perform a perception task using the respective feature vectors.

RISK-BASED TRUST SCORING AND OPERATIONALIZATION FRAMEWORK FOR GENERATIVE ARTIFICIAL INTELLIGENCE MODELS

Resumen de: WO2026170170A1

A method for providing a Generative Artificial Intelligence (GenAI) system with trustworthiness evaluation, wherein the method comprises processing a training dataset that the GenAI was trained upon; constructing a plurality of latent knowledge anchors (LKAs) by applying topic modeling on the processed training dataset, wherein the plurality of LKAs comprises domain-specific knowledge representations within the processed training dataset; training a neural network classifier using the LKAs and the processed training data; evaluating, using the neural network classifier, a response generated by the GenAI to generate a trust score, wherein the trust score indicates the alignment level of the response to the training dataset and/or the comprehensiveness of the response compared to the training dataset; in response to the trust score exceeding a threshold, presenting the response to a user; and in response to the trust score not exceeding the threshold, issuing a command for the GenAI to conduct additional actions.

DEVICE SETTINGS OPTIMIZATION

Resumen de: WO2026169963A1

A method for optimizing device settings of a plurality of devices includes receiving a performance characteristics target for devices manufactured according to a common design, wherein each device is configurable via device settings and exhibits performance variations over process variations and device operating conditions. The method includes defining a plurality of test cases, each including a combination of a respective device, a process variation, and a device operating condition. The method includes applying a first genetic adaptation algorithm to produce test results, training a neural network to generate predicted performance characteristics, and determining, by using the trained neural network as a surrogate model and applying a second genetic adaptation algorithm, a global set of device settings that collectively achieves the performance characteristics target across the plurality of devices.

SYSTEMS, APPARATUSES, AND METHODS FOR MONITORING ORGAN HEALTH

Resumen de: WO2026169639A1

A system for training at least one graph neural network (GNN) for monitoring organ health includes at least one memory configured to store instructions and at least one processor configured to execute the instructions to cause the system to obtain a plurality of parameters from healthy individuals and diseased individuals, perform causal discovery to determine one or more causal relationships between the plurality of organ parameters, train the at least one GNN with the one or more causal relationships to create a trained GNN configured to output a multi-organ health status based on patient parameters. The system is also configured to train at least one acute event prediction model to predict at least one acute or adverse event for at least one organ

THREE-DIMENSIONAL BASE CALLING IN NEXT GENERATION SEQUENCING ANALYSIS

Resumen de: AU2025214687A1

Disclosed herein are sequencing systems and sequencing methods for training neural networks and for utilizing the trained neural networks for sequencing analysis after acquiring flow cell images using the sequencing systems. The sequencing systems disclosed herein can include Field-Programmable Gate Array (FPGAs), artificial intelligence (AI) chips, or a combination thereof.

DETERMINING OBJECT ORIENTATION FROM AN IMAGE WITH MACHINE LEARNING

Resumen de: US20260237177A1

Apparatuses, systems, and techniques to determine orientation of an objects in an image. In at least one embodiment, images are processed using a neural network trained to determine orientation of an object.

TECHNIQUE TO PERFORM NEURAL NETWORK ARCHITECTURE SEARCH WITH FEDERATED LEARNING

Resumen de: US20260236742A1

Apparatuses, systems, and techniques to select a neural network architecture from a plurality of neural networks in a federated learning (FL) setting. In at least one embodiment, a neural network is trained by combining training results from different FL computing systems, where each of the different FL computing systems, for example, trains different portions of the neural network.

NEURAL NETWORKS WITH SUBDOMAIN TRAINING

Resumen de: US20260236778A1

0000 Heterogenous neural networks are disclosed that have activation functions that hold multi-variable equations. These variables can be passed from one neuron to another. The neurons may be laid out in a topologically similar fashion to a physical system that the heterogenous neural network is modeling. A neural network may have inputs of more than one type. Only a portion of the inputs (a subdomain) may be optimized In such an instance, the neural network may run forward, backpropagate to all inputs, and then perform optimization only on those inputs which will be optimized.

QUANTUM, BIOLOGICAL, COMPUTER VISION, AND NEURAL NETWORK SYSTEMS FOR INDUSTRIAL INTERNET OF THINGS

Resumen de: AU2026208040A1

Abstract Computer-implemented method transmits a predictive model from a first device to a second device. The first device receives data values of a data stream comprising sensor data collected from one or more sensor devices in an industrial environment. Using the received data values, the first device generates and refines a first predictive model for predicting future data values, including determining and adjusting predictive model parameters based on newly received data values. The first device transmits the predictive model parameters to the second device. The second device receives the predictive model parameters and parameterizes a second predictive model using the received parameters. The second predictive model predicts future values of the first device. Based at least in part on the predicted future values, the second device causes a physical control action to be performed with respect to a physical component in the industrial environment. The predictive model parameters may be updated and retransmitted during operation. Abstract to FIG. 3 Self Organizing Network Coding to FIG. 2 Data Pool Predictive Trained Diagnostics Maintenance Models Data Rights Config. Semantic Semantic System Pool Management Automation Processing Pricing Policy Decision User Order Analysis Automation Engine Analytics Private Cloud Ad and Anticipation Location Based Customer Storage Content Targeting of State Services Applications Analytics Expert Pattern Speech Other Services Dynamic Systems

NEURAL NETWORK-BASED IMAGE LIGHTING

Resumen de: US20260237124A1

Apparatuses, systems, and techniques are presented to generate image data. In at least one embodiment, one or more neural networks are used to cause a lighting effect to be applied to one or more objects within one or more images based, at least in part, on synthetically generated images of the one or more objects.

CLASS AGNOSTIC OBJECT MASK GENERATION

Resumen de: US20260237074A1

Class agnostic object mask generation uses a vision transformer-based auto-labeling framework requiring only images and object bounding boxes to generate object (segmentation) masks. The generated object masks, images, and object labels may then be used to train instance segmentation models or other neural networks to localize and segment objects with pixel-level accuracy.

CONTROLLING AGENTS USING Q-TRANSFORMER NEURAL NETWORKS

Resumen de: US20260236740A1

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for controlling an agent interacting with an environment using a Transformer neural network.

FINGERPRINT INDEXING USING CONVOLUTIONAL NEURAL NETWORK

Resumen de: US20260236527A1

A method of filtering fingerprint candidates, the method being carried out by an indexing module arranged to access a Convolutional Neuronal Network, CNN configured to output at least one feature of an input image. The method comprises processing an image representative of local information of a searched fingerprint, by the CNN to obtain at least one feature for the searched fingerprint; retrieving a candidate fingerprint in a database; determining whether at least one feature of the retrieved candidate fingerprint matches with the at least one feature of the searched fingerprint; if the at least one feature of the retrieved candidate fingerprint matches with the at least one feature of the searched fingerprint, passing the at least one candidate fingerprint to a matching module for further comparison between the candidate fingerprint and the searched fingerprint. Other aspects are also considered.

DIGITAL IMAGE PROCESSING FOR GENERATING MULTI-CHANNEL IMAGES

Resumen de: WO2026169910A1

Systems, apparatuses, and methods disclosed herein relate to a digital image processing system. In one aspect, the digital image processing system includes one or more processors and one or more computer-readable media storing instructions which, when executed by the one or more processors, cause the digital image processing system to access a digital image depicting a portion of a biological sample obtained from a subject. A projecting space and a staining category for an image conversion is defined by the digital image processing system, causing the digital image to be projected to the projecting space using a neural network model. The projected image is output by the digital image processing system.

NEURAL NETWORK TRAINING METHOD AND RELATED DEVICE

Resumen de: EP4790604A1

Embodiments of this application disclose a neural network training method. A first module in a federated neural network is deployed in each of a plurality of first devices. The first module includes a feature extraction module. A plurality of second modules in the federated neural network and early exit modules connected to the respective second modules are deployed in a second device. It can be learned that, in a federated learning process, the second device may include a plurality of early exit nodes, and each early exit node corresponds to one second module and a corresponding early exit module connected to the second module. In this way, after federated learning, when a target network is deployed in the first device, a structure of the target network may be in a plurality of forms based on the plurality of early exit nodes. In other words, target networks of different structures may be flexibly deployed in different first devices. For example, flexible scheduling may be performed based on resource statuses of different first devices, so that each first device can implement efficient data processing through a target network of an appropriate scale.

DEVICE FOR ACQUIRING MAGNETIC RESONANCE IMAGE ON BASIS OF DEEP LEARNING MODEL AND CONTROL METHOD THEREOF

Resumen de: EP4790443A1

The present disclosure provides an apparatus for restoring the quality of magnetic resonance images based on a deep learning model and a method of controlling the same. The method includes: obtaining a training image corresponding to each magnetic resonance image by applying at least one of a plurality of elements set in connection with the quality of the magnetic resonance image to a magnetic resonance signal corresponding to the magnetic resonance image; obtaining a training dataset including the magnetic resonance image as label data and the obtained training image as input data matching the label data; and training a neural network model based on the training dataset and context data corresponding to the training image. Obtaining the training image includes distorting the magnetic resonance signal by applying the at least one of the plurality of elements and obtaining the training image based on the distorted magnetic resonance signal.

GENERALIZED ENERGY DISTANCE DIFFUSION MODELS

Resumen de: WO2026165379A1

A method for generating a data item using a generative neural network model comprises, at each of a plurality of iterations, the generative neural network model processing a network input based on a current version of a data representation, to form a network output. The generative neural network is trained to form the network output as a sample from a target probability distribution over the representation space. The data representation is a vector defined in a representation space, and in each iteration, the network output is used to generate an updated data representation. The data item is generated based on the updated data representation generated in the last iteration.

MAPPING IMAGES TO WORDS FOR COMPOSED IMAGE RETRIEVAL

Resumen de: US20260228272A1

0000 Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for composed image retrieval. In one aspect, a method performed by one or more computers is described. The method includes: receiving a query including: (i) an image depicting a scene, and (ii) a text prompt describing a context of the scene; processing the image, using a visual encoder, to generate a visual embedding of the image; processing the visual embedding of the image, using a mapping neural network, to generate one or more language tokens of the image; generating multiple language tokens of the text prompt; processing the language tokens of the image and text prompt, using a language encoder, to generate a language embedding of the query; and selecting, from a number candidate images, one or more of the candidate images using the language embedding of the query.

PIPELINED MATRIX MULTIPLICATION AT A GRAPHICS PROCESSING UNIT

Resumen de: US20260228302A1

A graphics processing unit (GPU) schedules recurrent matrix multiplication operations at different subsets of CUs of the GPU. The GPU includes a scheduler that receives sets of recurrent matrix multiplication operations, such as multiplication operations associated with a recurrent neural network (RNN). The multiple operations associated with, for example, an RNN layer are fused into a single kernel, which is scheduled by the scheduler such that one work group is assigned per compute unit, thus assigning different ones of the recurrent matrix multiplication operations to different subsets of the CUs of the GPU. In addition, via software synchronization of the different workgroups, the GPU pipelines the assigned matrix multiplication operations so that each subset of CUs provides corresponding multiplication results to a different subset, and so that each subset of CUs executes at least a portion of the multiplication operations concurrently.

TRANSFORMER-BASED SHAPE MATCHING ACROSS IMAGES

Resumen de: WO2026165126A1

A system for matching shapes between images includes a transformer-based neural network with an encoder processing input images and a decoder processing a query shape from a first image. A parallel decoding module estimates corresponding shapes in a second image based on processed feature maps and query shapes from the first image. The system may include a recursive zoom-in module that iteratively refines the estimated corresponding shapes by zooming into regions around initial estimates to achieve sub-pixel accuracy. The transformer-based neural network can be trained using a data generation process that adapts based on training loss curves.

DYNAMIC CLASS-INCREMENTAL LEARNING WITHOUT FORGETTING

Resumen de: US20260228525A1

A processor-implemented method for dynamic class-incremental learning without forgetting includes receiving, by an artificial neural network (ANN), an input. The ANN extracts features of the input to generate a representation of the input. An embedding is generated by the ANN based on the representation and multiple similarity metrics. The ANN generates a new class without retraining the ANN. The new class is generated based on a comparison of the embedding and a set of prior embeddings.

OPTIMIZING PARAMETER ESTIMATION FOR TRAINING NEURAL NETWORKS

Nº publicación: US20260228308A1 06/08/2026

Solicitante:

NVIDIA CORP [US]
NVIDIA Corporation

Resumen de: US20260228308A1

Apparatuses, systems, and techniques estimate parameters to train one or more neural networks based on uniqueuss of training data. In at least one embodiment, a subset of training data is selected and used to estimate parameters to train one or more neural networks, based on, for example, uniqueness of training data.