Redes Neuronais

FRAMEWORK FOR CAUSAL LEARNING OF NEURAL NETWORKS

Resumen de: US2025181912A1

Disclosed herein is the framework of causal cooperative networks that discovers the causal relationship between observational data in a dataset and a label of the observation thereof and trains each model with inference of a causal explanation, reasoning, and production. In the case of the supervised learning, neural networks are adjusted through the prediction of the label for observation inputs. On the other hand, a causal cooperative network that includes the explainer, a reasoner, and a producer neural network models, receives an observation and a label as a pair, results multiple outputs, and calculates a set of losses of inference, generation, and reconstruction from the input and the outputs. The explainer, the reasoner, and the producer are adjusted by error propagation for each model obtained from the set of losses.

STEP-UNROLLED DENOISING NEURAL NETWORKS

Resumen de: US2025181897A1

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating output sequences using a non-auto-regressive neural network.

DILATED CONVOLUTIONS AND GATING FOR EFFICIENT KEYWORD SPOTTING

Resumen de: US2025174225A1

A method for detection of a keyword in a continuous stream of audio signal, by using a dilated convolutional neural network, implemented by one or more computers embedded on a device, the dilated convolutional network comprising a plurality of dilation layers, including an input layer and an output layer, each layer of the plurality of dilation layers comprising gated activation units, and skip-connections to the output layer, the dilated convolutional network being configured to generate an output detection signal when a predetermined keyword is present in the continuous stream of audio signal, the generation of the output detection signal being based on a sequence of successive measurements provided to the input layer, each successive measurement of the sequence being measured on a corresponding frame from a sequence of successive frames extracted from the continuous stream of audio signal, at a plurality of successive time steps.

LIFELONG MACHINE LEARNING (LML) MODEL FOR PATIENT SUBPOPULATION IDENTIFICATION USING REAL-WORLD HEALTHCARE DATA

Resumen de: US2025173563A1

A deep learning model implements continuous, lifelong machine learning (LML) based on a Bayesian neural network using a framework including wide, deep, and prior components that use available real-world healthcare data differently to improve prediction performance. The outputs from each component of the framework are combined to produce a final output that may be utilized as a prior structure when the deep learning model is refreshed with new data in a deep learning process. Lifelong learning is implemented by dynamically integrating present learning from the wide and deep learning components with past learning from models in the prior component into future predictions. The Bayesian deep neural network-based LML model increases accuracy in identifying patient profiles by continuously learning, as new data becomes available, without forgetting prior knowledge.

INCREMENTAL PRECISION NETWORKS USING RESIDUAL INFERENCE AND FINE-GRAIN QUANTIZATION

Resumen de: US2025173567A1

One embodiment provides for a computer-readable medium storing instructions that cause one or more processors to perform operations comprising determining a per-layer scale factor to apply to tensor data associated with layers of a neural network model and converting the tensor data to converted tensor data. The tensor data may be converted from a floating point datatype to a second datatype that is an 8-bit datatype. The instructions further cause the one or more processors to generate an output tensor based on the converted tensor data and the per-layer scale factor.

METHOD AND CONTROLLER FOR GENERATING A PREDICTIVE MAINTENANCE ALERT

Resumen de: US2025172933A1

A graph has nodes which represent entities of the industrial system and edges representing relations between the entities of the industrial system. A graph neural network processing the graph calculates a class prediction for at least one entity of the industrial system. A sub-symbolic explainer processes the class prediction to identify edges between nodes and associated features of nodes belonging to a sub-graph within the graph having influenced the class prediction. A large language model, equipped with a plugin for accessing the graph and receiving a prompt including the sub-graph, transforms the sub-graph into a maintenance justification in natural language. A user interface outputs a predictive maintenance alert along with the maintenance justification.

ELECTRONIC DEVICE AND METHOD OF LOW LATENCY SPEECH ENHANCEMENT USING AUTOREGRESSIVE CONDITIONING-BASED NEURAL NETWORK MODEL

Resumen de: US2024161736A1

A neural method model is trained by, in an initial training iteration, training the neural network model in a teacher forcing mode in which an autoregressive channel includes a ground-truth shifted waveform, and outputting predictions of the neural network model; and in at least one additional training iteration, replacing the ground-truth shifted waveform in the autoregressive channel with the predictions of the neural network model obtained in a previous training iteration. An inference may then be performed by providing, for the neural network model, an additional channel containing at least one prediction of the neural network model outputted during training; and performing speech enhancement using the neural network model.

COMPUTE OPTIMIZATION MECHANISM FOR DEEP NEURAL NETWORKS

Resumen de: US2025166115A1

Embodiments provide mechanisms to facilitate compute operations for deep neural networks. One embodiment comprises a graphics processing unit comprising one or more multiprocessors, at least one of the one or more multiprocessors including a register file to store a plurality of different types of operands and a plurality of processing cores. The plurality of processing cores includes a first set of processing cores of a first type and a second set of processing cores of a second type. The first set of processing cores are associated with a first memory channel and the second set of processing cores are associated with a second memory channel.

TRAINING A SOUND EFFECT RECOMMENDATION NETWORK

Resumen de: US2025165789A1

A Sound effect recommendation network is trained using a machine learning algorithm with a reference image, a positive audio embedding and a negative audio embedding as inputs to train a visual-to-audio correlation neural network to output a smaller distance between the positive audio embedding and the reference image than the negative audio embedding and the reference image. The visual-to-audio correlation neural network is trained to identify one or more visual elements in the reference image and map the one or more visual elements to one or more sound categories or subcategories within an audio database.

UTILIZATION-BASED MAPPING FOR THREE DIMENSIONAL ANALOG IN-MEMORY COMPUTING

Resumen de: US2025165769A1

A method for balancing utilization of tiles in an analog in-memory computing system includes identifying, by a computer processor, a plurality of tiles in the analog in-memory computing system. The computer processor receives a plurality of layers in a neural network being processed by the analog in-memory computing system. The computer processor maps the plurality of layers in the neural network to the plurality of tiles. The computer processor determines a number of operations for each of the tiles in the plurality of tiles. The computer processor determines an equalized utilization rate for the tiles in the plurality of tiles. In addition, the computer processor assigns the layers to the plurality of tiles. The tiles are assigned so that a first utilization rate of a first tile is balanced relative to a second utilization rate of a second tile in the analog in-memory computing system.

STORING LEARNED EMBEDDINGS OF SEQUENCE STATES

Resumen de: US2025156733A1

A method for computing a prediction using a machine learning model includes: receiving a current data sample of a sequence of data samples; retrieving, from a data store, a state value representing a learned embedding of previous samples of the sequence of data samples; computing, by a recurrent neural network, based on the current data sample and the state value: an output value representing an inference regarding the current data sample; and an updated state value representing a learned embedding of the current data sample and the previous samples of the sequence of data samples; storing the updated state value in the data store; and outputting the output value regarding the current data sample.

MACHINE LEARNING-BASED AUTOMATED ABNORMALITY DETECTION IN MEDICAL IMAGES AND PRESENTATION THEREOF

Resumen de: US2025156677A1

The presently disclosed technology relates to medical image processing. An example method includes receiving medical image data which represents an anatomical structure and processing the received image data through convolutional neural network (CNN) to generate predictions. The predictions can include abnormality location proposals and abnormality class probabilities associated with each abnormality location proposals.

MACHINE LEARNING-BASED AUTOMATED ABNORMALITY DETECTION IN MEDICAL IMAGES AND PRESENTATION THEREOF

Resumen de: US2025156676A1

The presently disclosed technology relates to medical image processing. An example method includes receiving medical image data which represents an anatomical structure and processing the received image data through convolutional neural network (CNN) to generate predictions. The predictions can include abnormality location proposals and abnormality class probabilities associated with each abnormality location proposals.

NEURAL NETWORK UTILIZATION WITH ULTRASOUND TECHNOLOGY

Resumen de: US2025157038A1

Examples herein include methods, systems, and computer program products for utilizing neural networks in ultrasound systems. The methods include processor(s) of a computing device identifying a neural network for implementation on the computing device to generate, based on ultrasound data, inferences and confidence levels for the inferences, the computing device being communicatively coupled via a computing network to an ultrasound machine configured to generate the ultrasound data. The processor(s) implements the neural network on the computing device, including configuring the neural network to generate an inference and a confidence level for at least one image of the images. The processor(s) obtains the ultrasound data including images from the ultrasound machine. The processor(s) determines, for the at least one image, an accuracy of the inference and the confidence level. The processor(s) automatically reconfigures the neural network to increase the accuracy based on the determining the accuracy.

Explanatory Integrity Evaluation Method and System

Resumen de: US2025156735A1

An explanatory integrity evaluation method and system evaluates potential facts and associated potential conclusions that are embodied by syntactical elements that are generated by one or more computer-implemented neural networks that are trained on content that includes a plurality of syntactical elements. The explanatory integrity evaluations may include fact sensitivity and causal factor analyses, assessing probabilistic reasoning, performing searches, and/or evaluating and selecting from alternative explanations. Probabilities that the potential facts and associated potential conclusions represent object reality may be determined. Explanatory quality scores may be generated with respect to combinations of potential facts and potential conclusions, which may inform communications to users.

MULTI-BRANCH NETWORK ARCHITECTURE SEARCHING SYSTEM AND METHOD

Resumen de: US2025156727A1

A multi-branch network architecture searching method includes: obtaining a training dataset with a plurality of input data; obtaining block design elements for blocks, wherein the blocks forms an architecture of a neural network, and the blocks are configured to perform a feature extraction on the input data to generate an output data; for each hyperparameter of the neural network, obtaining at least one hyperparameter setting value; inputting the training dataset, block design elements, and the at least one hyperparameter setting value into a hyperparameter optimization algorithm to generate a hyperparameter combination, wherein the hyperparameter combination includes one of the at least one hyperparameter setting corresponding to each hyperparameter; executing the neural network based on the hyperparameter combination and inputting a test dataset to evaluate a model performance of the neural network; and outputting the hyperparameter combination when the model performance reaches a threshold.

Neural Network Training Method of Measurement for Similarity Between Process-Sequences And Measuring Apparatus Operating Method Of Thereof

Resumen de: KR20250067678A

실시예는, 유사도 계산을 위한 학습 방법과 유사도 계산을 위한 계산 장치 및 동작 방법에 관한 것이다. 실시예에 계산 장치의 동작 방법은, 제1 학습 파라미터에 기초하여, 제1 공정 시퀀스의 제1 공정 프로세스들 및 제2 공정 시퀀스에 포함되는 제2 공정 프로세스들의 벡터들을 각각 임베딩하는 단계; 제2 학습 파라미터에 기초하여, 상기 제1 공정 프로세스들에 대응하는 제1 임베딩 벡터들과 상기 제2 공정 프로세스들에 대응하는 제2 임베딩 벡터들을 서로 매핑하는 단계; 및 상기 매핑 결과에 기초하여, 상기 제1 공정 시퀀스와 상기 제2 공정 시퀀스의 유사도를 계산하는 단계를 포함할 수 있다.

High Frequency QRS in Biometric Identification

Resumen de: AU2025202887A1

Abstract Disclosed is sampling HF-QRS signals from a number of subjects (or derived values or features), and using e.g. deep learning-convolutional neural networks to find features or values which are (i) sufficiently similar for the same subject over all samples, yet (ii) sufficiently different among different subjects to allow identification. Also disclosed is finding signatures which are sufficiently stable over a particular period such that these signatures are within a deviation threshold, and then monitoring all subjects to be identified at least as often as the period used to establish the deviation threshold.

TECHNIQUES FOR LEARNING CO-ENGAGEMENT AND SEMANTIC RELATIONSHIPS USING GRAPH NEURAL NETWORKS

Resumen de: WO2025101527A1

One embodiment of a method for training a machine learning model includes generating a graph based on one or more semantic concepts associated with a plurality of entities and user engagement with the plurality of entities, and performing one or more operations to train an untrained machine learning model based on the graph to generate a trained machine learning model.

METHOD AND APARATUS FOR DETECTION AND PREVENTION OF ANOMALOUS ACTIVITIES IN NEW CONTEXTS

Resumen de: WO2025098649A1

The present disclosure relates to artificial intelligence systems employing machine learning that allow to predict anomalous activities and / events and to identify, optimize and decide on suitable counter measures. An aspect relates to a computer- implemented method for predicting behavior and/or relations of objects in a target region that are associated with anomalous types of behavior and / or relations, the method comprising, obtaining a plurality of data sets characterizing behavior and/or relations of the objects in the target region for a plurality of time intervals, generating, based on the obtained plurality of data sets, a first graph and, optionally, a second graph for the plurality of objects in the target region, wherein the first graph characterizes behavior and/or relations of the objects in the target region that are not associated with anomalous types of behavior and / or relations, and wherein the optional second graph characterizes behavior and/or relations of the objects in the target region that are associated with anomalous types of behavior and / or relations and predicting, using a trained neural network model, and based on the generated first graph and the optional second graph the behavior and/or relations of the objects in the target region that are associated with anomalous types of behavior and / or relations. Further aspects relate to associated methods for preventing occurrences of such anomalous types of behavior and / or relations as well as

CONVOLUTIONAL NEURAL NETWORK OPTIMIZATION MECHANISM

Resumen de: EP4553752A2

Herein, an apparatus for optimization of a convolutional neural network (CNN) model after the CNN model has been trained and is ready to be deployed, is provided. The apparatus comprises: a graphics processing unit (GPU) including one or more graphics processors. The GPU implements an optimization mechanism including primitives to implement quantization and de-quantization operations. The GPU receives the CNN model, the CNN model having been trained using a training data set representing a problem being modeled by the CNN model; sets a quantization table to enable nonuniform quantization of data associated with the CNN model, wherein generating the quantization table includes executing a quantization primitive provided by the optimization mechanism; quantizes floating-point data associated with the CNN model from a floating-point format to an 8-bit integer format using the quantization table; and performs an inference operation utilizing the CNN model with the quantized data in the 8-bit integer format.

SYSTEMS AND METHODS FOR INTERPRETABLE CLASSIFICATION OF IMAGES USING INHERENTLY EXPLAINABLE NEURAL NETWORKS

Resumen de: US2025037446A1

An artificial intelligence-based image processing system comprises a processor that executes instructions stored on a memory to classify an input image with a prototypical part neural network including a backbone subnetwork, a prototype subnetwork, and a readout subnetwork to produce an interpretable classification of the input image including one or a combination of a classification result of the input image and an interpretation of the classification result. The backbone subnetwork is trained with machine learning to process the input image with an incomplete sequence of active convolutional layers producing feature embeddings representing features extracted from pixels of different regions of the input image. The prototype subnetwork is trained to compare the feature embeddings with prototypical feature embeddings to produce results of comparison and the readout subnetwork is configured to analyze the results of comparison to produce the interpretable classification of the input image.

TECHNIQUES FOR LEARNING CO-ENGAGEMENT AND SEMANTIC RELATIONSHIPS USING GRAPH NEURAL NETWORKS

Resumen de: US2025148280A1

One embodiment of a method for training a machine learning model includes generating a graph based on one or more semantic concepts associated with a plurality of entities and user engagement with the plurality of entities, and performing one or more operations to train an untrained machine learning model based on the graph to generate a trained machine learning model.

FUNCTIONAL ACTIVATION-BASED ANALYSIS OF DEEP NEURAL NETWORKS

Resumen de: WO2025097127A1

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.

TRAINING ACTION SELECTION NEURAL NETWORKS USING LOOK-AHEAD SEARCH

Nº publicación: US2025148282A1 08/05/2025

Solicitante:

DEEPMIND TECH LIMITED [GB]
DeepMind Technologies Limited

Resumen de: US2025148282A1

Methods, systems and apparatus, including computer programs encoded on computer storage media, for training an action selection neural network. One of the methods includes receiving an observation characterizing a current state of the environment; determining a target network output for the observation by performing a look ahead search of possible future states of the environment starting from the current state until the environment reaches a possible future state that satisfies one or more termination criteria, wherein the look ahead search is guided by the neural network in accordance with current values of the network parameters; selecting an action to be performed by the agent in response to the observation using the target network output generated by performing the look ahead search; and storing, in an exploration history data store, the target network output in association with the observation for use in updating the current values of the network parameters.