Xarxes Neuronals

MODULAR ARTIFICIAL INTELLIGENCE PLATFORM FOR MEDIA GENERATION AND METHODS FOR USE THEREWITH

Resumen de: EP4517581A1

A modular artificial intelligence (AI) platform operates by: receiving media input that includes image data and text data; generating encoded text data via a text encoder module that includes first language processing AI; generating encoded image data via an image encoder module that includes a plurality of neural networks and a long short-term memory; generating concept structure data via a concept identification module that includes graph-based learning AI; generating decoded text data via a text decoder module that includes language processing AI; generating decoded image data, via an image decoder module that includes a plurality of neural networks and a long short-term memory; and combining the decoded image data and the decoded text data to generate media output data.

DEEP NEURAL NETWORK-BASED SEQUENCING

Resumen de: US2025069704A1

A system, a method and a non-transitory computer readable storage medium for base calling are described. The base calling method includes processing through a neural network first image data comprising images of clusters and their surrounding background captured by a sequencing system for one or more sequencing cycles of a sequencing run. The base calling method further includes producing a base call for one or more of the clusters of the one or more sequencing cycles of the sequencing run.

Augmenting Retrieval Systems With User-Provided Phonetic Signals

Resumen de: US2025069593A1

A method includes obtaining, from a user device associated with a user, an audio signature, the audio signature extracted from audio data corresponding to a query spoken by the user. The method also includes processing, using a neural network, the audio signature to identify document tokens that match the audio signature within a shared embedding space, the neural network trained to jointly embed audio signatures and document tokens in the shared embedding space. The method also includes retrieving, using the document tokens and the shared embedding space, a set of search results for the query, and providing, for output from the user device, one or more search results from the set of search results to the user.

CREATING DIVERSE NEURAL NETWORKS WITH NODE TYING

Resumen de: US2025068909A1

A system and method for controlling a nodal network. The method includes estimating an effect on the objective caused by the existence or non-existence of a direct connection between a pair of nodes and changing a structure of the nodal network based at least in part on the estimate of the effect. A nodal network includes a strict partially ordered set, a weighted directed acyclic graph, an artificial neural network, and/or a layered feed-forward neural network.

COOPERATIVELY TRAINING AND/OR USING SEPARATE INPUT AND SUBSEQUENT CONTENT NEURAL NETWORKS FOR INFORMATION RETRIEVAL

Resumen de: US2025068913A1

Systems, methods, and computer readable media related to information retrieval. Some implementations are related to training and/or using a relevance model for information retrieval. The relevance model includes an input neural network model and a subsequent content neural network model. The input neural network model and the subsequent content neural network model can be separate, but trained and/or used cooperatively. The input neural network model and the subsequent content neural network model can be “separate” in that separate inputs are applied to the neural network models, and each of the neural network models is used to generate its own feature vector based on its applied input. A comparison of the feature vectors generated based on the separate network models can then be performed, where the comparison indicates relevance of the input applied to the input neural network model to the separate input applied to the subsequent content neural network model.

INFERENCING USING NEURAL NETWORKS

Resumen de: US2025069358A1

Apparatuses, systems, and techniques to use data obtained from an inferred object to determine whether to re-infer the same inferred object. In at least one embodiment, one or more objects are identified in one or more images. A size of the one or more objects in one image is compared to a size of the one or more objects in another image. The one or more objects are re-inferenced based, at least in part, on the comparison.

METHOD AND APPARATUS WITH NEURAL NETWORK DEVICE PERFORMANCE AND POWER EFFICIENCY PREDICTION

Resumen de: US2025068938A1

A processor-implemented method includes obtaining a benchmark execution result, receiving input data comprising a neural network model subject to prediction and analysis requirement information, receiving information on hardware of a device in which the neural network model is run, building a prediction model based on the benchmark execution result and the hardware information, extracting layer information respectively corresponding to a plurality of layers configuring the neural network model, and predicting either one or both of operation performance information and energy efficiency information respectively corresponding to the plurality of layers by inputting the analysis requirement information and the layer information to the prediction model.

SYSTEMS, METHODS, AND COMPUTER-READABLE MEDIA FOR IMPROVED TABLE IDENTIFICATION USING A NEURAL NETWORK

Resumen de: US2025068837A1

Systems, methods, and computer-readable storage devices are disclosed for improved table identification in a spreadsheet. One method including: receiving a spreadsheet including at least one table; identifying, using machine learning, one or more classes of a plurality of classes for each cell of the received spreadsheet, wherein the plurality of classes include corners and not-a-corner; and inducing at least one table in the received spreadsheet based on the one or more identified classes for each cell of the received spreadsheet.

METHODS AND SYSTEMS FOR IMPLEMENTING SECURE AND TRUSTWORTHY ARTIFICIAL INTELLIGENCE

Resumen de: WO2025042692A1

Provided herein are systems, methods, computer-readable media, and techniques for providing trusted artificial intelligence (AI) using Fully Homomorphic Encryption (FHE), comprising: (A) providing a deep neural network (DNN)-based model with modified architecture, wherein the modified architecture at least (i) uses a Gaussian function as an activation function and (ii) removes one or more pooling layers; (B) obtaining encrypted data, wherein the encrypted data are generated by applying the FHE to plaintext data; and (C) generating an inference with the DNN-based model based on the encrypted data. Further provided herein are systems, methods, computer-readable media, and techniques for providing trusted AI using stochastic computing, using noise based computing, using an artificial immune system, and with secure multi-party computation (SMPC) based at least in part on watermarking.

SYSTEM AND METHOD FOR HUMAN ACTIVITY RECOGNITION

Resumen de: AU2023324756A1

In aspects, the present approaches allow neural networks to be taught to understand patterns of human behavior without the need of expert data labeling or laboratory studies. First and second neural networks are trained to understand these patterns without labeling. Once trained, the neural networks can be deployed with a trained classifier to determine or classify human activity based upon received sensor inputs.

METHOD FOR DETERMINING RELATIVE ENERGY BETWEEN SYSTEMS, AND ELECTRONIC DEVICE

Resumen de: EP4513385A1

The present disclosure relates to a method and apparatus for determining a relative energy between systems, an electronic device, a computer-readable storage medium, and a computer program product. The method (300) includes: for a chemical system, performing a plurality of iteration rounds using a neural network variational Monte Carlo method (310); acquiring a linear relationship between energy errors and energy variances, which are obtained in the plurality of iteration rounds (320); determining a first energy error at a position where the energy variance is zero based on the linear relationship (330); and determining the relative energy between the chemical system and a further system based on the first energy error (340). It can be seen that, since there is no need to wait for complete convergence of training in the solution, the required time is less, and the efficiency is higher.

Computer Vision Systems and Methods for End-to-End Training of Convolutional Neural Networks Using Differentiable Dual-Decomposition Techniques

Resumen de: US2025061577A1

Computer vision systems and methods for end-to end training of neural networks are provided. The system generates a fixed point algorithm for dual-decomposition of a maximum-a-posteriori inference problem and trains the convolutional neural network and a conditional random field with the fixed point algorithm and a plurality of images of a dataset to learn to perform semantic image segmentation. The system can segment an attribute of an image of the dataset by the trained neural network and the conditional random field.

METHODS AND SYSTEMS FOR AN INTELLIGENT TECHNICAL DEBT HELPER BOT

Resumen de: US2025061043A1

Methods and systems for an intelligent technical debt helper may include receiving, via a processor, a level of technical debt associated with a technical debt of a computer program code and determining, via the processor, whether the level of technical debt is greater than a technical debt threshold. The method may also include generating, using an artificial intelligence neural network model communicatively coupled to the processor and based on the computer program code, an automated code recommendation to address the technical debt of the computer program code when the level of technical debt is greater than the technical debt threshold.

SCALING HALF-PRECISION FLOATING POINT TENSORS FOR TRAINING DEEP NEURAL NETWORKS

Resumen de: US2025061318A1

One embodiment provides for a machine-learning accelerator device a multiprocessor to execute parallel threads of an instruction stream, the multiprocessor including a compute unit, the compute unit including a set of functional units, each functional unit to execute at least one of the parallel threads of the instruction stream. The compute unit includes compute logic configured to execute a single instruction to scale an input tensor associated with a layer of a neural network according to a scale factor, the input tensor stored in a floating-point data type, the compute logic to scale the input tensor to enable a data distribution of data of the input tensor to be represented by a 16-bit floating point data type.

ITERATIVE SPATIAL GRAPH GENERATION

Resumen de: US2025061153A1

A generative model can be used for generation of spatial layouts and graphs. Such a model can progressively grow these layouts and graphs based on local statistics, where nodes can represent spatial control points of the layout, and edges can represent segments or paths between nodes, such as may correspond to road segments. A generative model can utilize an encoder-decoder architecture where the encoder is a recurrent neural network (RNN) that encodes local incoming paths into a node and the decoder is another RNN that generates outgoing nodes and edges connecting an existing node to the newly generated nodes. Generation is done iteratively, and can finish once all nodes are visited or another end condition is satisfied. Such a model can generate layouts by additionally conditioning on a set of attributes, giving control to a user in generating the layout.

SYSTEM AND METHOD FOR TUMOR CHARACTERIZATION

Resumen de: US2025061149A1

A method of treating a subject comprises administering a treatment to a subject identified as having a high probability of distant metastatic recurrence, wherein the probability of distant metastatic recurrence was determined by a process, comprising acquiring at least one image of a tissue sample comprising a plurality of cells, taken from a subject, classifying each of the plurality of cells into categories, dividing the at least one image into a plurality of patches, calculating values for a plurality of morphological features based on the patches, and calculating a distant metastatic recurrence probability based on the values. A computer-implemented method of training a neural network and a system for characterizing a cancer in a subject are also described.

FLUID FLOW SIMULATION

Resumen de: EP4510034A1

A method of using a computer implemented neural network for a simulation of aerodynamic performance of a technical object having a geometry, the method comprising:Training the neural network using a plurality of sets of encodings of pre-computed computational fluid dynamics, CFD, outputs, wherein the training is generated using inputs comprising:a geometry of at least one training technical object;spatial locations of input nodes of the neural network as node attributes;a relationship between the geometry of the at least one training technical object and the neural network input node locations;associated boundary conditions;operating conditions; andcomputed outputs comprising flow fields and aerodynamic performance parameters;the training using a loss function that evaluates an error between a neural network output and the pre-computed CFD outputs to produce a trained neural network;using the trained neural network with new inputs to generate as output a predicted aerodynamic performance of the technical object, wherein the relationship between the geometry of the at least one training technical object and the neural network input node locations comprises a vector with at least two parameters.

METHOD AND DEVICE FOR ON-DEVICE LEARNING BASED ON MULTIPLE INSTANCES OF INFERENCE WORKLOADS

Resumen de: US2025053807A1

The present disclosure relates to a method of training a neural network using a circuit comprising a memory and a processing device, an exemplary method comprising: performing a first forward inference pass through the neural network based on input features to generate first activations, and generating an error based on a target value, and storing the error to the memory; and performing, for each layer of the neural network: a modulated forward inference pass; before, during or after the modulated forward inference pass, a second forward inference pass based on the input features to regenerate one or more first activations; and updating one or more weights in the neural network based on the modulated activations and the one or more regenerated first activations.

COMPUTE OPTIMIZATION MECHANISM FOR DEEP NEURAL NETWORKS

Resumen de: US2025053797A1

An apparatus to facilitate compute optimization is disclosed. The apparatus includes a at least one processor to perform operations to implement a neural network and compute logic to accelerate neural network computations.

GENERATING INTEGRATED CIRCUIT FLOORPLANS USING NEURAL NETWORKS

Resumen de: US2025053714A1

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating a computer chip floorplan. One of the methods includes obtaining netlist data for a computer chip; and generating a computer chip floorplan, comprising placing a respective node at each time step in a sequence comprising a plurality of time steps, the placing comprising, for each time step: generating an input representation for the time step; processing the input representation using a node placement neural network having a plurality of network parameters, wherein the node placement neural network is configured to process the input representation in accordance with current values of the network parameters to generate a score distribution over a plurality of positions on the surface of the computer chip; and assigning the node to be placed at the time step to a position from the plurality of positions using the score distribution.

EFFICIENT NEURAL NETWORKS WITH ELABORATE MATRIX STRUCTURES IN MACHINE LEARNING ENVIRONMENTS

Resumen de: US2025053814A1

A mechanism is described for facilitating slimming of neural networks in machine learning environments. A method of embodiments, as described herein, includes learning a first neural network associated with machine learning processes to be performed by a processor of a computing device, where learning includes analyzing a plurality of channels associated with one or more layers of the first neural network. The method may further include computing a plurality of scaling factors to be associated with the plurality of channels such that each channel is assigned a scaling factor, wherein each scaling factor to indicate relevance of a corresponding channel within the first neural network. The method may further include pruning the first neural network into a second neural network by removing one or more channels of the plurality of channels having low relevance as indicated by one or more scaling factors of the plurality of scaling factors assigned to the one or more channels.

CRITICAL NODE DETECTION

Resumen de: WO2025034710A1

A computer-implemented method for optimizing neural networks by detecting critical and non-critical nodes is disclosed. The method involves obtaining a neural network comprising a plurality of nodes and their weighted connections. Critical nodes, which have a greater correlation to the network's output than non-critical nodes, are identified through a two-step detection process. The first critical node detection process identifies critical nodes based on weighted direct connections among the nodes. The second critical node detection process identifies critical nodes based on unweighted direct and indirect connections. The configuration of the neural network is then adjusted based on the identified critical and non-critical nodes to improve efficiency or reduce size.

INPUT DATA TRANSFORMATION FRAMEWORK FOR LOW-VOLTAGE MODEL

Resumen de: US2025053802A1

Aspects of the invention include techniques for improving the accuracy of access-limited neural network inference in low-voltage regimes. A non-limiting example method includes training a first machine learning model to perform input transformation for reducing low-voltage bit errors for a deep neural network operating in a low-voltage regime. The training includes inputting training data into the first machine learning model such that, in response, the first machine learning model produces transformed training data; inputting the transformed training data into a clean machine learning model and into perturbed machine learning models, the perturbed machine learning models being generated by applying random bit errors to the clean machine learning model; and optimizing the first machine learning model based on a comparison of output of the clean machine learning model and of the perturbed machine learning models compared to groundtruth labels for the training data.

STOCHASTIC OPTIMIZATION USING MACHINE LEARNING

Resumen de: US2025045577A1

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for performing stochastic optimization using machine learning. One of the methods includes obtaining data defining a multi-stage stochastic optimization (MSSO) problem instance, the data characterizing an observation distribution, an action space, and a cost function; generating a neural network input characterizing the MSSO problem instance from the data; providing the neural network input as input to a neural network that generates, from the network input, a neural network output characterizing parameters of a value function corresponding to the MSSO problem instance; processing the neural network input using the neural network to generate the neural network output; obtaining a new observation determined according to the observation distribution for the MSSO problem instance; determining, using the value function characterized by the network output, an optimal action to take in response to the new observation; and executing the optimal action.

METHOD FOR A WEB SCRAPING TOOL AND CLASSIFICATION ENGINE

Nº publicación: US2025045323A1 06/02/2025

Solicitante:

ZYTE GROUP LTD [IE]
Zyte Group Limited

Resumen de: US2025045323A1

A web scaping system configured with artificial intelligence and image object detection. The system processes a web page with a neural network to perform object detection to obtain structured data, including text, image and other kinds of data, from web pages. The neural network allows the system to efficiently process visual information (including screenshots), text content and HTML structure to achieve good quality and decrease extraction time.