Absstract of: 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.
Absstract of: 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.
Absstract of: 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.
Absstract of: 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.
Absstract of: 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.
Absstract of: 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
Absstract of: 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.
Absstract of: 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.
Absstract of: 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.
Absstract of: 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.
Absstract of: 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.
Absstract of: 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.
Absstract of: 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.
Absstract of: 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.
Absstract of: US2025148562A1
A system processes images of documents, for example, identification documents. The system transforms an image of a document to generate an image that represent the document in a canonical form. For example, if the input image has a document that is tilted at an angle with respect to the sides of the image, the system modifies the orientation of the document to show the document having sides aligned with the sides of the image. The system stores user accounts that include user information including images. The system generates a graph of nodes that represent user accounts with edges determined based on similarity scores between user accounts. The system determines connected components of user accounts, such that each connected component represents user accounts that have a high likelihood of being duplicates.
Absstract of: 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.
Absstract of: 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.
Absstract of: US2025138544A1
A system for managing energy usage in a vehicle is provided. The system includes a vehicle control system, an artificial intelligence system, and an energy management module. The vehicle control system is operable to adjust at least one operational parameter of the vehicle. The artificial intelligence (AI) system includes a hybrid neural network configured to: process vehicle operational state and energy consumption information; classify a plurality of operational states of the vehicle; and determine an optimized vehicle operating state based on the classified operational states. The energy management module is coupled to the AI system and the vehicle control system, and: receives operational state and energy consumption information from the vehicle; and modifies the at least one operational parameter to optimize electricity usage of the vehicle.
Absstract of: US2025139409A1
Computer systems and computer-implemented methods train a neural network, by:(a) computing for each datum in a set of training data, activation values for nodes in the neural network and estimates of partial derivatives of an objective function for the neural network for the nodes in the neural network; (b) selecting a target node of the neural network and/or a target datum in the set of training data; (c) selecting a target-specific improvement model for the neural network, wherein the target-specific improvement model, when added to the neural network, improves performance of the neural network for the target node and/or the target datum, as the case may be; (d) training the target-specific improvement model; (e) merging the target-specific improvement model with the neural network to form an expanded neural network; and (f) training the expanded neural network.
Absstract of: US2025131914A1
An aspect of the present invention provides a learning device including: a neural network that converts an acoustic time series that is a time series representing a sound into feature data expressed in a predetermined format required by a downstream task; and an update unit that updates the neural network on the basis of an execution result of the downstream task using the feature data, in which the neural network includes: a feature extraction unit that converts an input acoustic time series into an intermediate feature tensor that is a third-order tensor indicating features of the acoustic time series and is a tensor having time, frequency, and channel; and an intermediate network that executes processing of converting a representation of the intermediate feature tensor into a representation of a second-order tensor having time and direct product amounts that are amounts indicating a direct product of frequency and channel, and processing of acquiring, for each direct product amount of the second-order tensor, a one-dimensional vector indicating a statistic in a time axis direction of each direct product amount as the feature data.
Nº publicación: US2025131920A1 24/04/2025
Applicant:
SYNTIANT [US]
SYNTIANT
Absstract of: US2025131920A1
Provided herein is an integrated circuit including, in some embodiments, a special-purpose host processor, a neuromorphic co-processor, and a communications interface between the host processor and the co-processor configured to transmit information therebetween. The special-purpose host processor is operable as a stand-alone host processor. The neuromorphic co-processor includes an artificial neural network. The co-processor is configured to enhance special-purpose processing of the host processor through the artificial neural network. In such embodiments, the host processor is a keyword identifier processor configured to transmit one or more detected words to the co-processor over the communications interface. The co-processor is configured to transmit recognized words, or other sounds, to the host processor.