Alerta

ANOMALY DETECTING EDGE DEVICE WITH QUANTIZED DEEP NEURAL NETWORK ON FPGA, ASIC, OR SOC

Resumen de: WO2025255347A1

Systems and methods are described for an edge device with a chip-implemented, reduced-bit-quantized neural network (NN)-based anomaly detector, including a preprocessing logic block for preprocessing the sensor data, and a quantized, processing-in-memory (PIM) based NN block. The quantized PIM-based NN block includes quantized multiply-accumulate units (MACs) with quantized PIM logic that uses quantized-arithmetic-result lookup tables. The quantized MACs are arranged to function as quantized, PIM-based NN block kernels. Optionally, the quantized PIM- based NN block is implemented as an autoencoder with a quantized NN encoding and a quantized NN decoding section. The quantized NN encoder section performs NN-based, quantized dimensionality reduction of the processed sensor data, outputting a quantized lower-dimensional latent representation. The quantized NN decoder section reconstructs the quantized lower-dimensional latent representation, producing a quantized reconstructed input pattern. The quantized NN encoder and decoder sections include quantized MACs with PIM logic using quantized- arithmetic-result lookup tables.

SPARSITY CONTROL BASED ON HARDWARE FOR DEEP-NEURAL NETWORKS

Resumen de: US2025378334A1

Systems, methods, computer program products, and apparatuses to transform a weight space of an inference model to increase the compute efficiency of a target inference platform. A density of a weight space can be determined, and a transformation parameter derived based on the determined density. The weight space can be re-ordered based on the transformation parameter to balance the compute load between the processing elements (PEs) of the target platform, and as such, reduce the idle time and/or stalls of the PEs.

INFORMATION PROCESSING METHOD AND APPARATUS, DEVICE, AND STORAGE MEDIUM

Resumen de: WO2025251721A1

According to embodiments of the present disclosure, provided are an information processing method and apparatus, a device, and a storage medium. The method comprises: determining a target processing layer from among a plurality of processing layers of a graph neural network, wherein a processing procedure corresponding to the target processing layer comprises a plurality of sub-processing procedures independent of each other; splitting the target processing layer into a plurality of sub-layers corresponding to the plurality of sub-processing procedures; using a plurality of processing devices to respectively process the plurality of sub-processing procedures corresponding to the plurality of sub-layers; and using a plurality of output results of processing of the plurality of processing devices in a summary layer corresponding to the plurality of sub-layers to determine a target output result for the target processing layer.

PERSONALIZED GENERATIVE NEURAL NETWORKS

Resumen de: WO2025254658A1

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for generating personalized output data items using a generative neural network. In one aspect, one of the method includes maintaining a respective set of adaptation parameters of a generative neural network for each of a plurality of predetermined content providers; obtaining a new input associated with a new content provider; using a classifier model to generate a respective score for each of the plurality of predetermined content providers; generating a new set of adaptation parameters based on determining a weighted combination of the respective set of adaptation parameters for each of a subset of the plurality of predetermined content providers; and generating, by the generative neural network and based on the new set of adaptation parameters and the new input, a new personalized output data item.

PREDICTION OF EQUIPMENT-RELATED EVENTS USING MACHINE LEARNING

Resumen de: US2025370446A1

Techniques are disclosed herein for machine-learning (ML)-assisted event prediction for industrial machines. A first set of embeddings can be generated based on labeled first event data, which can be labeled with classifiers determined based on signaling channel information for the first event data. A neural network can be trained, using the classifiers, to generate (i) a similarity score for the first set of embeddings and the second set of embeddings and (ii) a classifier recommendation for the second set of embeddings. The second set of embeddings can be generated based on data collected using condition monitoring sensors for a particular industrial machine. Accordingly, the system can generate alerts, recommendations, and/or notifications based on the automatically classified data encoded in the second set of embeddings. Incremental training techniques are disclosed for further training the neural network to minimize false positives and/or false negatives.

METHODS AND SYSTEMS FOR PROBABILISTIC RELATIONAL LEARNING

Resumen de: WO2025247606A1

Methods and systems for fully quantifying predictive uncertainty for recommender systems are disclosed. Embodiments include providing a fully Bayesian multiway neural network model, assigning a prior distribution over a plurality of weight parameters of a model parameter set of the neural network model such that a corresponding posterior distribution represents an epistemic uncertainty of the neural network model; incorporating a mixture density model for a target layer of the neural network model, wherein the mixture density model models aleatoric uncertainty of input data; estimating the posterior distribution of the weight parameters given training data by updating the prior distribution based on data likelihood of the training data; sampling a plurality of empirical samples from the estimated posterior distribution of the weight parameters; performing inference for each stochastic realization of the neural network model with the sampled weight parameters on an inference sample to generate one or more predictive distributions; drawing samples from each of the one or more predictive distributions as final predictions for the inference sample to obtain a matrix of predictions for the inference sample, wherein the matrix represents a joint distribution of both the aleatoric and epistemic uncertainty of the recommender system.

SYSTEMS AND METHODS FOR DEFINING CONFIDENCE IN DEEP LEARNING MODEL PREDICTION

Resumen de: US2025371340A1

The invention relates to a technique for improving confidence estimates associated with neural networks. The technique involves computing neuron activation statistics during training, evaluating neuron activations during inferencing and determining how the activations compare with the previously computed statistics (e.g. whether prediction activations are within the bounds of the training activation statistics). The comparison may be used to compute a confidence value for the neural network.

PREDICTION OF EQUIPMENT-RELATED EVENTS USING MACHINE LEARNING

Resumen de: WO2025250329A1

Techniques are disclosed herein for machine-learning (ML)-assisted event prediction for industrial machines (106). A first set of embeddings (1986a) can be generated based on labeled first event data, which can be labeled with classifiers (1989b) determined based on signaling channel (110b) information for the first event data. A neural network (300) can be trained, using the classifiers (1989b), to generate (i) a similarity score for the first set of embeddings and the second set of embeddings and (ii) a classifier (1989b) recommendation for the second set of embeddings. The second set of embeddings can be generated based on data collected using condition monitoring sensors (104a) for a particular industrial machine. Accordingly, the system (200) can generate alerts, recommendations, and/or notifications based on the automatically classified data encoded in the second set of embeddings.

SPEAKER IDENTIFICATION, VERIFICATION, AND DIARIZATION USING NEURAL NETWORKS FOR CONVERSATIONAL AI SYSTEMS AND APPLICATIONS

Resumen de: US2025372084A1

Disclosed are apparatuses, systems, and techniques that may use machine learning for implementing speaker recognition, verification, and/or diarization. The techniques include applying a neural network (NN) to a speech data to obtain a speaker embedding representative of an association between the speech data and a speaker that produced the speech. The speech data includes a plurality of frames and a plurality of channels representative of spectral content of the speech data. The NN has one or more blocks of neurons that include a first branch performing convolutions of the speech data across the plurality of channels and across the plurality of frames and a second branch performing convolutions of the speech data across the plurality of channels. Obtained speaker embeddings may be used for various tasks of speaker identification, verification, and/or diarization.

METHODS AND SYSTEMS FOR PROBABILISTIC RELATIONAL LEARNING

Resumen de: EP4657316A1

Methods and systems for fully quantifying predictive uncertainty for recommender systems are disclosed. Embodiments include providing a fully Bayesian multiway neural network model, assigning a prior distribution over a plurality of weight parameters of a model parameter set of the neural network model such that a corresponding posterior distribution represents an epistemic uncertainty of the neural network model; incorporating a mixture density model for a target layer of the neural network model, wherein the mixture density model models aleatoric uncertainty of input data; estimating the posterior distribution of the weight parameters given training data by updating the prior distribution based on data likelihood of the training data; sampling a plurality of empirical samples from the estimated posterior distribution of the weight parameters; performing inference for each stochastic realization of the neural network model with the sampled weight parameters on an inference sample to generate one or more predictive distributions; drawing samples from each of the one or more predictive distributions as final predictions for the inference sample to obtain a matrix of predictions for the inference sample, wherein the matrix represents a joint distribution of both the aleatoric and epistemic uncertainty of the recommender system.

DECODING QUANTUM ERROR CORRECTION CODES USING TRANSFORMER NEURAL NETWORKS

Resumen de: WO2024157242A1

Transformer neural network based decoder for decoding Quantum Error Correction Codes (QECC), comprising, an input layer, a plurality of decoding layers, and an output layer. The input layer is adapted to receive initial noise estimation computed by a noise estimator for noise injected to syndrome bits of codewords encoded using QECC and transmitted over transmission channel(s) subject to interference, and create embeddings for the syndrome bits. The decoding layers adapted to compute an estimated logical operator matrix of each codeword, each comprises a self-attention layer constructed according to a mask indicative of a relation between the embeddings derived from a parity-check matrix of the error correction code. The plurality of decoding layers are trained using a combined loss function directed to minimize LER, BER, and error rate of the noise estimator. The output layer is adapted to produce a vector representing predicted soft error of the codeword's logical operator matrix.

SYSTEMS AND METHODS FOR DEFINING CONFIDENCE IN DEEP LEARNING MODEL PREDICTION

Resumen de: EP4657324A1

The invention relates to a technique for improving confidence estimates associated with neural networks. The technique involves computing neuron activation statistics during training, evaluating neuron activations during inferencing and determining how the activations compare with the previously computed statistics (e.g. whether prediction activations are within the bounds of the training activation statistics). The comparison may be used to compute a confidence value for the neural network.

SUBGRAPH PATTERN EXTRACTION

Resumen de: US2025363328A1

Aspects of the disclosed technology provide solutions for extracting subgraph patterns in graph-structured data and encoding them as embeddings using a graph neural network (GNN). In some aspects, a process of the disclosed technology can include steps for receiving an input graph comprising a plurality of nodes and edges, the input graph representing relationships among a plurality of entities, parameterizing a graph neural network model based on a set of pattern graphs, and identifying, for at least a portion of the nodes in the input graph, rooted homomorphisms between the pattern graphs and local subgraphs rooted at the respective nodes. Systems and machine-readable media are also provided.

MACHINE LEARNING METHODS FOR PREDICTING PROPERTIES OF PROTEINS AND LIGANDS

Resumen de: US2025364082A1

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for generating a predicted property score of a protein and a ligand. In one aspect, a method comprises: obtaining a network input that characterizes a protein and a ligand; processing the network input characterizing the protein and the ligand using an embedding neural network to generate a protein-ligand embedding representing the protein and the ligand, wherein the embedding neural network has been jointly trained with a generative model that is configured to: receive an input protein-ligand embedding; and generate, while conditioned on the input protein-ligand embedding, a predicted joint three-dimensional (3D) structure of an input protein and an input ligand represented by the input protein-ligand embedding; and generating a property score that defines a predicted property of the protein and the ligand using the protein-ligand embedding.

PREDICTING PROPERTIES OF PROTEINS AND LIGANDS

Resumen de: EP4654205A1

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for generating a predicted property score of a protein and a ligand. In one aspect, a method comprises: obtaining a network input that characterizes a protein and a ligand; processing the network input characterizing the protein and the ligand using an embedding neural network to generate a protein-ligand embedding representing the protein and the ligand, wherein the embedding neural network has been jointly trained with a generative model that is configured to: receive an input protein-ligand embedding; and generate, while conditioned on the input protein-ligand embedding, a predicted joint three-dimensional (3D) structure of an input protein and an input ligand represented by the input protein-ligand embedding; and generating a property score that defines a predicted property of the protein and the ligand using the protein-ligand embedding.

INFORMATION PROCESSING DEVICE, INFORMATION PROCESSING METHOD, AND PROGRAM

Resumen de: WO2025239034A1

The present invention realizes a process for efficiently constructing an optimal neural network corresponding to a new task by utilizing existing neural network structure information. A new neural network corresponding to a specific task is constructed by analyzing existing neural network structure information and source code, performing module-based segmentation processing and processing for generating a parent hierarchical graph structure, analyzing the generated parent hierarchical graph structure, and generating a new child hierarchical graph structure corresponding to the specific task. Furthermore, an optimal neural network can be constructed by generating a child hierarchical graph structure by referring to a configuration file in which the existing neural network configuration information is recorded, and evaluation information.

1 SYSTEM AND METHOD FOR CUSTOMER JOURNEY EVENT REPRESENTATION LEARNING AND OUTCOME PREDICTION USING NEURAL SEQUENCE MODELS

Resumen de: AU2025263751A1

A system and method are presented for customer journey event representation learning and outcome prediction using neural sequence models. A plurality of events are input into a module where each event has a schema comprising characteristics of the events and their modalities (web clicks, calls, emails, chats, etc.). The events of different modalities can be captured using different schemas and therefore embodiments described herein are schema-agnostic. Each event is represented as a vector of some number of numbers by the module with a plurality of vectors being generated in total for each customer visit. The vectors are then used in sequence learning to predict real-time next best actions or outcome probabilities in a customer journey using machine learning algorithms such as recurrent neural networks. A system and method are presented for customer journey event representation learning and outcome prediction using neural sequence models. A plurality of events are input into a module where each event has a schema comprising characteristics of the events and their modalities (web clicks, calls, emails, chats, etc.). The events of different modalities can be captured using different schemas and therefore embodiments described herein are schema-agnostic. Each event is represented as a vector of some number of numbers by the module with a plurality of vectors being generated in total for each customer visit. The vectors are then used in sequence learning to predict real-time next

SENSOR-PROCESSING SYSTEMS INCLUDING NEUROMORPHIC PROCESSING MODULES AND METHODS THEREOF

Resumen de: EP4651036A2

Disclosed is a sensor-processing system including, in some embodiments, a sensor, one or more sample pre-processing modules, one or more sample-processing modules, one or more neuromorphic integrated circuits ("ICs"), and a microcontroller. The one or more sample pre-processing modules are configured to process raw sensor data for use in the sensor-processing system. The one or more sample-processing modules are configured to process pre-processed sensor data including extracting features from the pre-processed sensor data. Each of the neuromorphic ICs includes at least one neural network configured to arrive at actionable decisions of the neural network from the features extracted from the pre-processed sensor data. The microcontroller includes a CPU along with memory including instructions for operating the sensor-processing system. In some embodiments, the sensor is a pulse-density modulation ("PDM") microphone, and the sensor-processing system is configured for keyword spotting. Also disclosed are methods of such a keyword spotting sensor-processing system.

METHOD AND APPARATUS FOR GENERATING INSTRUCTION SEQUENCE, ELECTRONIC DEVICE, AND STORAGE MEDIUM

Nº publicación: EP4650945A1 19/11/2025

Solicitante:

BEIJING HORIZON INFORMATION TECH CO LTD [CN]
Beijing Horizon Information Technology Co., Ltd

Resumen de: EP4650945A1

Disclosed are a method and apparatus for generating an instruction sequence, an electronic device, and a storage medium. The method for generating an instruction sequence includes: determining a computation graph corresponding to a neural network model to be compiled and resource status information on hardware executing the instruction sequence; partitioning the computation graph, to determine multiple computation sub-graphs; generating, based on the computation sub-graphs and the resource status information, instruction sub-sequences corresponding respectively to the computation sub-graphs; and determining, based on the instruction sub-sequences, a target instruction sequence corresponding to the neural network model to be compiled.