Alerta

TRAINING A NEURAL NETWORK TO SIMULTANEOUSLY ASCERTAIN SEMANTIC INFORMATON AND DEPTH INFORMATION

Absstract of: US20260154979A1

0000 A method for training an image processing neural network. The method includes: providing a set of training images; feeding each training image to a first trained neural network, which assigns semantic information to pixels, other image portions, and/or image features of an input image; feeding each training image to a second trained neural network, which assigns depth information to pixels, other image portions, and/or image features of an input image; fusing the semantic information and depth information to form a target map, which assigns semantic information to locations in three-dimensional space; processing, using the image processing neural network to be trained, each training image to form a map, which assigns semantic information to locations in three-dimensional space; checking, using a cost function, to what extent the map thus obtained is in line with the target map; optimizing parameters that characterize the behavior of the image processing neural network.

NEURAL NETWORK TRAINING USING RESAMPLED IMAGE DATA

Absstract of: US20260154378A1

0000 Apparatuses, systems, and techniques to modify a set of training data used for machine learning. In at least one embodiment, a set of images used for training a machine learning system is resampled by augmenting the set of images with additional images of under represented object types extracted from portions of existing training images in the set.

Highly Efficient Convolutional Neural Networks

Absstract of: US20260154533A1

0000 The present disclosure provides directed to new, more efficient neural network architectures. As one example, in some implementations, the neural network architectures of the present disclosure can include a linear bottleneck layer positioned structurally prior to and/or after one or more convolutional layers, such as, for example, one or more depthwise separable convolutional layers. As another example, in some implementations, the neural network architectures of the present disclosure can include one or more inverted residual blocks where the input and output of the inverted residual block are thin bottleneck layers, while an intermediate layer is an expanded representation. For example, the expanded representation can include one or more convolutional layers, such as, for example, one or more depthwise separable convolutional layers. A residual shortcut connection can exist between the thin bottleneck layers that play a role of an input and output of the inverted residual block.

METHOD FOR PREDICTING GROWTH BASED ON GROWTH AGE USING ARTIFICIAL INTELLIGENCE MODEL AND PROVIDING SOLUTION THEREFOR

Absstract of: US20260154568A1

0000 A method for predicting growth on the basis of growth age and providing a solution by using an artificial intelligence model may include the steps of: receiving biometric data of a measurement target; extracting data regarding the predicted age of peak height velocity (APHV), at which the growth velocity is expected to reach the maximum value, by using the biometric data of the measurement target; classifying the growth step of the measurement target into one of multiple growth steps on the basis of the extracted data regarding the predicted APHV; predicting the final height by inputting the extracted data regarding the predicted APHV into a trained neural network; and providing a growth management solution on the basis of the classified growth step and the predicted final height.

A CERVICAL INTRAEPITHELIAL NEOPLASIA RISK PREDICTION MODEL AND ITS CONSTRUCTION METHOD, AN ELECTRONIC DEVICE, AND A STORAGE MEDIUM

Absstract of: NL4000831A

The present invention belongs to the technical field of deep learning and discloses a cervical intraepithelial neoplasia risk prediction model and its construction method, an electronic device, and a storage medium. The method includes: a data sample acquisition step; a data analysis step, screening the original significant features; constructing a decision tree model using the original significant features as input data, obtaining the prediction result of each sample; extracting the prediction result as new significant features; merging the original significant features and the new significant features into an extended feature set, using the extended feature set to train an artificial neural network model, obtaining the cervical intraepithelial neoplasia risk prediction model. The present invention, by integrating decision tree and artificial neural network and combining clinical screening indicators, realizes cervical intraepithelial neoplasia risk assessment, improves the prediction accuracy and robustness, and greatly improves clinical diagnosis efficiency.

Method And System for Manufacturing Fiber Bragg Grating Based on Machine Vision

Absstract of: AU2025204589A1

The present disclosure relates to the field of laser micro-nano manufacturing technology and discloses a method and system for manufacturing a fiber Bragg grating based on machine vision. By combining advanced machine vision technology and neural network model technology, automatic recognition of the focal plane of the fiber core is realized, so that the laser focus can be automatically focused on the focal plane of the fiber core, thereby realizing the automatic and intelligent fiber Bragg grating manufacturing process. The method not only has the characteristics of high precision and high efficiency, but also shows broad application prospects, providing strong support for the development of optical fiber communication, sensing, and other fields. (Fig. 1) The present disclosure relates to the field of laser micro-nano manufacturing technology and discloses a method and system for manufacturing a fiber Bragg grating based on machine vision. By combining advanced machine vision technology and neural network model technology, automatic recognition of the focal plane of the fiber core is realized, SO that the laser focus can be automatically focused on the focal plane of the fiber core, thereby realizing the automatic and intelligent fiber Bragg grating manufacturing process. The method not only has the characteristics of high precision and high efficiency, but also shows broad application prospects, providing strong support for the development of optical fiber communication, se

MACHINE LEARNING APPARATUS, MACHINE LEARNING METHOD, AND COMPUTER READABLE NON-TRANSITORY RECORDING MEDIUM STORING MACHINE LEARNING PROGRAM

Absstract of: US20260154549A1

A linguistic feature amount output part receives a text describing a base class image and outputs a linguistic feature amount. An image feature amount output part receives the base class image and outputs an image feature amount. A base class image selection part receives the linguistic feature amount, the image feature amount, and the base class image and selects a base class image corresponding to the image feature amount having a distance equal to or smaller than a predetermined threshold value from the linguistic feature amount. A neural network lower layer part receives the base class image selected by the base class image selection part and a novel class image and outputs a value based the base class image and a value based on the novel class image. A base class classification output part outputs a base class classification based on the base class image and the novel class image. A novel class classification output part outputs a novel class classification based on the novel class image.

MULTI-NODE CLUSTER-BASED INFERENCE METHOD AND SYSTEM THROUGH GPU SEPARATE ALLOCATION OF PRE-TRAINED LAYER AND FINE-TUNING LAYER OF MULTIPLE DEEP LEARNING MODELS

Absstract of: US20260154775A1

0000 A multi-node cluster-based inference method through GPU separation allocation of a pre-trained layer and a fine-tuning layer of multiple deep learning models. The method includes: receiving an input value from a client; distributing the received input value, and transmitting the first input value to a first computation node including a container in which a neural network bundle of a first stage is loaded; performing, by a first container of the first computation nodes, an operation through a neural network layer of a GPU by using the received first input value as an input, and generating a first output value; and selecting a container in which the neural network bundle of the next stage is loaded, and transmitting the second output value to the computation node that includes the container in which the next stage is to be executed or the container in which to execute the next stage.

RELIABILITY PREDICTION METHOD FOR IMAGE CLASSIFICATION NEURAL NETWORK MODEL

Absstract of: US20260154949A1

0000 A reliability prediction method for an image classification neural network model includes: a reliability model is trained; and the trained reliability model predicts a reliability of the image classification neural network model. According to training and testing of the image classification neural network model, input features of the reliability model include a model training factor and a model testing factor. The model training factor characterizes data and model factors affecting the reliability of the image classification neural network model. The model testing factor characterizes a test sufficiency of the image classification neural network model. An output of the reliability model is a reliability prediction result of the image classification neural network model.

IMAGE GENERATION USING A NEURAL NETWORK

Absstract of: US20260154963A1

0000 Apparatuses, systems, and techniques to generate an image. In at least one embodiment, one or more neural networks are to generate a second image based, at least in part, on a first image and information indicating zero or more differences between the first and second image.

VIDEO SYNTHESIS WITHIN A MESSAGING SYSTEM

Absstract of: EP4752837A2

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.

METHOD FOR CONTROLLING VEHICLE POWER, COMPUTER SYSTEM, AND VEHICLE

Absstract of: EP4751988A1

0001 A method for controlling vehicle power, a computer system, and a vehicle are disclosed. The vehicle includes a fuel cell, a power battery, a hydraulic system, an accessory system, and a visual sensor. The method is performed by a processing circuit of a computer system. The method includes obtaining an image of a construction earthwork by the visual sensor; identifying a type of the construction earthwork by an earthwork classification model based on the image of the construction earthwork; obtaining a power demand load spectrum of the vehicle within a first time duration; correcting the type of the construction earthwork based on the power demand load spectrum; inputting the power demand load spectrum and the corrected type of the construction earthwork into a pre-trained neural network prediction model, and predicting a power load spectrum of the vehicle within a second time duration by the neural network prediction model; and determining optimal power allocation between the fuel cell and the power battery based on the predicted power load spectrum, so as to minimize an operating cost objective function within the second time duration.

AI-driven system and method for generating style fingerprints and compositions

Absstract of: GB2644802A

The present invention relates to an Al-driven system for generating style transfer fingerprints and compositions. It includes modules for integrating with sonic libraries, extracting metadata and audio features, and employing deep neural networks for style transfer. A style fingerprint generation module captures the artist's sonic characteristics, stored securely in a database linked to artist profiles. A composition generation module utilizes these fingerprints to create new audio compositions that authentically reflect the artist's unique style. The method involves connecting the artist's library, preprocessing audio, extracting features, training a style transfer model, generating a style fingerprint, and producing compositions.

SYSTEM AND METHOD FOR DYNAMICALLY ADJUSTING LEVEL OF DETAILS OF POINT CLOUDS

Absstract of: EP4752843A2

Some embodiments of an example method disclosed herein may include receiving point cloud data representing one or more three-dimensional objects; receiving a viewpoint of the point cloud data; selecting a selected object from the one or more three-dimensional objects using the viewpoint; retrieving a neural network model for the selected object; generating a level of detail data for the selected object using the neural network model; and replacing, within the point cloud data, points corresponding to the selected object with the level of detail data.

ADAPTIVE REAL-TIME ADJUSTMENTS IN DEEP NEURAL NETWORKS

Nº publicación: EP4752786A1 03/06/2026

Applicant:

NOKIA SOLUTIONS & NETWORKS OY [FI]
Nokia Solutions and Networks Oy

Absstract of: EP4752786A1

In some embodiments, there may be provided a method that includes In some embodiments, there may be provided a method that includes receiving an indication to perform a single class inference task using a machine learning model that is trained to perform a multi-class inference task; in response to the indication, applying, during a timeframe of execution of the machine learning model hosted by the user equipment, at least one mask mapped to the single class inference task; and reconfiguring the machine learning model to a state where the first set of nodes and the second set to perform the multi-class inference task. Related systems, methods, and articles of manufacture are also disclosed.