Alerta

TECHNIQUES FOR ARTIFICIAL INTELLIGENCE CAPABILITIES AT A NETWORK SWITCH

Absstract of: US20260312885A1

0000 Examples include techniques for artificial intelligence (AI) capabilities at a network switch. These examples include receiving a request to register a neural network for loading to an inference resource located at the network switch and loading the neural network based on information included in the request to support an AI service to be provided by users requesting the AI service.

OBJECT IMAGE COMPLETION

Absstract of: US20260311379A1

Apparatuses, systems, and techniques to generate complete depictions of objects based on a partial depiction of the object. In at least one embodiment, an image of a complete object is generated by one or more neural networks, based on an image of a portion of the object, using an encoder of the one or more neural networks trained using training data generated from output of a decoder of the one or more neural networks.

SYSTEMS AND METHODS FOR IMPROVED IMAGE PROCESSING

Absstract of: US20260311475A1

0000 A system and method for training (and inference) of a NN model for wide/ultra-wide angle lens object detection and positioning, the NN training module configured to receive one or more images associated with one or more images from the object recognition data set, the data set including one or more bounding box labels associated with the one or more images, apply a customized data augmentation routine on said images to create one or more augmented images in each new iteration of training, provide a predetermined neural network for computer vision model to test and train the neural network for computer vision, predict and obtain a bounding box and confidence score, each being associated with one or more objects in the one or more images from the neural network for computer vision, match ground truth bounding boxes in image space to augmentations from a box data store, apply regression loss on the bounding boxes and compute the cost between predicted values and the label values to determine change in weightings.

Video Compression Method and Device with Multi-Scale Implicit Neural Representation

Absstract of: US20260311377A1

0000 A video processing method with multi-scale implicit neural representation includes: using an implicit neural network to convert an original video sequence into network parameters; using the implicit neural network to extract fused encoding features with temporal information and perform spatial decoding, where the fused encoding features are selected based on the original video sequence; constructing a loss function of the implicit neural network based on the original video sequence and a reconstructed video, where the reconstructed video is obtained by reconstructing the original video sequence; using the loss function to iteratively optimize the network parameters, where the final optimized network parameters are used as the video compression results corresponding to the original video sequence. Therefore, by adopting the video processing method, the spatial and temporal structural priors of the video can be fully leveraged, enabling the compression efficiency to reach optimal levels and improving video compression performance.

COMPUTER SYSTEM AND METHOD FOR MARITIME SURVEILLANCE AND SATELLITE-BASED EARTH OBSERVATION OF OBJECTS USING NADIR-OBLIQUE IMAGE MATCHING

Absstract of: US20260311486A1

0000 Systems, methods, and computer-readable media for vessel identification are provided. The system includes a data storage device storing: a database of optical oblique images each containing a known candidate vessel having a known unique vessel identifier; and an optical nadir satellite image containing an unknown vessel. The system further includes a processor configured to execute a nadir-oblique image matcher configured to: compare, via a neural network, the nadir image to oblique images in the database including determining a similarity score between the nadir image and a respective oblique image; output, via the neural network, a ranked list of the oblique images based on the determined similarity scores; and assign a known unique vessel identifier to the nadir image based on the ranked list.

MODULARIZED HOME ROBOT

Absstract of: US20260307239A1

0000 Implementations of a fully configurable, modularized home robot are described that implement trained neural network classifiers to solve problems of providing home health care and monitoring of the elderly and/or infirm, providing entertainment for the family, providing environmental and safety monitoring coupled with mechanisms to clean the air and remedy indoor climates such as humidity and temperature, and provide a mechanism for caring for pets left at home when the owner is away based upon sensory input.

METHOD FOR OPERATING NEURAL NETWORK

Absstract of: US20260310951A1

A method is provided and includes operations as below: receiving multiple spike signals in an input layer of a spiking neural network during multiple time steps; counting a corresponding number of spikes in the spike signals for each of the time steps; weighting, in response to the corresponding number of spikes in one of plurality of time steps being greater than a predetermined count value, the spike signals with multiple synaptic weight values to generate multiple synaptic signals; generating a membrane potential by accumulating a number N of the synaptic signals according to a weight distribution of the synaptic weight values; and generating an output spike signal according to the membrane potential.

SEQUENCE PACKING FOR TRAINING IMAGE PROCESSING NEURAL NETWORKS

Absstract of: US20260311467A1

0000 Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training an image processing neural network. For example, a method can include obtaining a batch of training examples, each training example comprising a respective training image; generating one or more input sequences, wherein each input sequence corresponds to two or more of the training images in the batch and is a sequence of tokens that comprises tokens representing patches from two or more corresponding training images; and processing each input sequence using the image processing neural network to generate a respective training output for each corresponding training image; and training the image processing neural network on a first loss function for the first task using the training outputs for the training images in the batch.

Identification of multi-scale features using neural network

Absstract of: AU2026234120A1

Apparatuses, systems, and techniques to identify features within one or more images. In at least one embodiment, features are identified in one or more images using one or more neural networks containing convolutional layers with multiple filters that may be executed by one or more parallel processing unit. ep e p

OPTICAL SENSING WITH NONLINEAR OPTICAL NEURAL NETWORKS

Absstract of: US20260310953A1

0000 Methods, devices, and systems for optical sensing with nonlinear optical neural network (ONNs) are provided. In one aspect, a method includes: receiving light from a visual scene by a first optical linear layer in a nonlinear ONN apparatus, linearly transforming the light into first optical outputs by the first optical linear layer trained to perform a first optical linear operation, non-linearly generating second optical outputs based on the first optical outputs by an optical nonlinear layer in the ONN apparatus, and linearly transforming the second optical outputs into third optical outputs by a second optical linear layer in the ONN apparatus trained to perform a second optical linear operation. The first optical linear layer, the optical nonlinear layer, and the second optical linear layer are sequentially arranged in series in the ONN apparatus.

PANORAMA GENERATION USING ONE OR MORE NEURAL NETWORKS

Absstract of: US20260311290A1

0000 Apparatuses, systems, and techniques are presented to generate panoramas from individual images. In at least one embodiment, one or more generative neural networks are used to generate a spherical panoramic image using features extracted from a single input image.

Neural Network Initialization

Absstract of: US20260310969A1

0000 A neural network representing a controlled space can be initialized by collecting state time series data that affects the controlled space such as weather, and also collecting sensor data from the controlled space at the same time. The time series data is used as input to a neural network that models the controlled space until an area in the neural network equivalent to the sensor is at or near the sensor state at a given time.

VIEW GENERATION USING ONE OR MORE NEURAL NETWORKS

Absstract of: US20260311378A1

Apparatuses, systems, and techniques are presented to generate image or video content representing at least one point of view. In at least one embodiment, one or more neural networks are used to generate one or more images of one or more objects from a first point of view based at least in part upon one or more images of the one or more objects from a second point of view.

OPTICAL INFORMATION READING DEVICE

Absstract of: US20260310918A1

To suppress an increase in processing time due to a load of inference processing while improving reading accuracy by the inference processing of machine learning. An optical information reading device includes a processor including: an inference processing part that inputs a code image to a neural network and executes inference processing of generating an ideal image corresponding to the code image; and a decoding processing part that executes first decoding processing of decoding the code image and second decoding processing of decoding the ideal image generated by the inference processing part. The processor executes the inference processing and the first decoding processing in parallel, and executes the second decoding processing after completion of the inference processing.

CONVOLUTIONAL NEURAL NETWORK STRUCTURE FOR EXPLAINABLE 3D SHAPE LEARNING, AND METHOD AND SYSTEM FOR 3D SHAPE LEARNING USING SAME

Absstract of: US20260311451A1

0000 Disclosed are a convolutional neural network structure for explainable 3D shape learning, and a method and a system for 3D shape learning by using same. A method for shape learning performed by a shape learning system according to an embodiment may comprise: extracting geodesic features and geometric features from three-dimensional shape data; and classifying an object through a convolution operation on the extracted geodesic features and the extracted geometric features with respect to faces constituting the three-dimensional shape data.

PERFORMING SEMANTIC SEGMENTATION OF 3D DATA USING DEEP LEARNING

Absstract of: US20260311336A1

0000 A computer-implemented method of training a deep artificial neural network includes receiving a three-dimensional point cloud and training the deep artificial neural network by subdividing the three-dimensional point cloud, and updating weights of the deep artificial neural network. A computing system includes a processor; and a memory having stored thereon computer-executable instructions that, when executed by the processor, cause the computing system to receive a three-dimensional point cloud and train the deep artificial neural network by subdividing the three-dimensional point cloud, and updating weights of the deep artificial neural network. In yet another aspect, a non-transitory computer-readable medium includes computer-executable instructions that when executed, cause a computer to receive a three-dimensional point cloud and train the deep artificial neural network by subdividing the three-dimensional point cloud, and updating weights of the deep artificial neural network.

DATA PROCESSING METHOD AND APPARATUS, ELECTRONIC DEVICE AND STORAGE MEDIUM

Absstract of: US20260310976A1

0000 Disclosed are a data processing method and apparatus, a storage medium, and an electronic device. A neural network is used to perform an inference operation on data to be processed, comprising successively performing M rounds of inference on the data to be processed, wherein the process of the i-th round of inference comprises: at a first stage, performing inference on N2 input data elements, and at a second stage, performing inference on N1 input data elements, the N1 input data elements, which belong to the same batch of input data, being a subset of the N2 input data elements; the inference process of the (i+1)-th round of inference comprises: for N2-N1 input data elements for which the inference is incomplete in the i-th round of inference but for which the output tokens have been acquired, performing inference on the N2-N1 input data elements while taking into account the output tokens.

TRAINING VISION LANGUAGE NEURAL NETWORKS WITH COMPONENT REUSE

Absstract of: US20260311476A1

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating and training a glued neural network that reuses components taken from a first pre-trained neural network and a second pre-trained neural network. For example, the first pre-trained neural network can be a multi-modal neural network that includes a visual encoder neural network and a small-scale language model neural network. The second pre-trained neural network can be a large-scale language model neural network.

TEMPORAL FEATURE SCALING FOR NEURAL NETWORK PROCESSING

Absstract of: US20260311361A1

Systems, devices, and methods described herein relate to feature scaling for neural network processing. In some examples, temporal feature scaling is employed for efficient neural network processing. To process the neural network, a processing system accesses feature maps of a current input frame in a temporal sequence of input frames and scales the feature maps of the current input frame using excitation values generated from a previous input frame in the temporal sequence. The processing system generates new excitation values from the current input frame to perform scaling for a subsequent input frame in the temporal sequence.

DEPTH AND MOTION ESTIMATIONS IN MACHINE LEARNING ENVIRONMENTS

Absstract of: US20260311478A1

A mechanism is described for facilitating depth and motion estimation in machine learning environments, according to one embodiment. A method of embodiments, as described herein, includes receiving a frame associated with a scene captured by one or more cameras of a computing device; processing the frame using a deep recurrent neural network architecture, wherein processing includes simultaneously predicating values associated with multiple loss functions corresponding to the frame; and estimating depth and motion based the predicted values.

METHOD FOR ATTENTION-DRIVEN TRAINING OF COMPUTER-IMPLEMENTED NEURAL NETWORKS USING DOMAIN KNOWLEDGE

Absstract of: EP4818980A1

0001 Die vorliegende Erfindung betrifft ein computerimplementiertes aufmerksamkeitsgesteuertes Trainingsverfahren zum Erhalt eines trainierten neuronalen Netzes für die Schädigungserkennung und/oder für die Erkennung mindestens eines Bereichs einer Rissspitze in einer Abbildung eines zu untersuchenden Körpers, ein computerimplementiertes Verfahren für die Schädigungserkennung in Bilddaten eines zu untersuchenden Körpers und dessen Verwendung, ein Prüfsystem, ein Computerprogrammprodukt sowie ein computerlesbares Speichermedium. Hierbei umfasst das Trainingsverfahren die Einbindung von Domänenwisssen zur Steuerung der Aufmerksamkeit während des Trainings.

Machine learning prediction of ion trap filling functions

Absstract of: GB2705175A

A method for facilitating machine learning prediction of ion trap filling functions is disclosed. The method comprises causing a mass analyser to perform a scan using an injection or accumulation time. The injection time is correlated to a requested or desired ion population size by an ion trap filling function, which may be non-linear. The coefficients of the ion trap filling function are predicted by a machine learning model based on current operational parameters of the mass analyser, e.g. the scan range or width of the mass analyser, pass range or width of an ion trap of the mass analyser, or the number of ion guide injections. The injection time may be scaled using a pre-scan ion flux estimate or an ion species distribution. The machine learning model may be trained in a supervised fashion and updated via backpropagation based on an error between the actual ion population size and the requested ion population size. The machine learning model may be a random forest regressor or a deep learning neural network. A system and a computer program are also claimed. Figure 15

CLINICAL SUPPORT SYSTEM AND ASSOCIATED COMPUTER-IMPLEMENTED METHODS

Absstract of: EP4819077A2

A clinical support system comprises a processor and a display component, wherein: the processor is configured to: receive image data, the image data representing an image of a plurality of cells obtained from a human or animal subject, the image data comprising a plurality of subsets of image data, each subset comprising data representing a portion of the image data corresponding to a respective cell of the plurality of cells; apply a trained deep learning neural network model to each subset of the image data, the deep learning neural network model comprising: a plurality of convolutional neural network layers each comprising a plurality of nodes; and a bottleneck layer comprising no more than ten nodes, wherein the processor is configured to apply the trained deep learning neural network model to each subset of the image data by applying the plurality of CNN layers, and subsequently applying the bottleneck layer, each node of the bottleneck layer of the machine-learning model configured to output a respective activation value for that subset of the image data; for each subset of the image data, derive a dataset comprising no more than three values, the values derived from the activation values of the nodes in the bottleneck layer; and generate instructions, which when executed by the display component of a clinical support system, cause the display component of the computer to display a plot in no more than three dimensions of the respective dataset of each subset of the ima

Driving scene search and driving policy training

Absstract of: GB2705187A

A computer-implemented method for storing and retrieving driving scenes, the method includes: determining one or more natural language descriptions of one or more driving scenes based on inputting, to a large language model, driving scene information of the one or more driving scenes and one or more prompts requesting the one or more natural language descriptions of the one or more driving scenes; creating one or more embeddings of the one or more natural language descriptions using a trained neural network and storing the one or more embeddings; receiving a natural language query associated with a query driving scene; creating an embedding of the natural language query using the trained neural network; selecting, from the one or more driving scenes, one or more similar driving scenes based on the one or more embeddings and the embedding of the natural language query; and outputting the selected one or more similar driving scenes. FIG. 3

NEURAL NETWORK TRAINING TECHNIQUE

Nº publicación: US20260300436A1 01/10/2026

Applicant:

NVIDIA CORP [US]
NVIDIA Corporation

Absstract of: US20260300436A1

0000 Apparatuses, systems, and techniques to train neural networks to perform image processing tasks. In at least one embodiment, one or more second neural networks are used to train one or more first neural networks based, at least in part, on a first object type in one or more images and a second object type in the one or more images, in parallel.